SlideShare uma empresa Scribd logo
1 de 38
Baixar para ler offline
Recent Advances in Kernel-Based Graph
Classification
ECML PKDD 2017, Nectar Track
Nils Kriege, Christopher Morris
June 20, 2017
TU Dortmund University, Algorithm Engineering Group
Motivation
Question
How similar are two graphs?
(a) Sildenafil (b) Vardenafil
1
High-level View: Supervised Graph Classification
⊆ H
φ
2
Primer on Graph Kernels
Question
How similar are two graphs?
Definition (Graph Kernel)
Let 𝒢 be a non-empty set of graphs and let k: 𝒢 × 𝒢 → R. Then k is
a graph kernel if there is a real Hilbert space ℋ and a feature map
𝜑: 𝒢 → ℋ such that k(G, H) = ⟨𝜑(G), 𝜑(H)⟩.
Explicit vs. Implicit
Exp.
(EX)
Imp.
(IM)
G H
Inner Product
PSD function
𝜑(G)
𝜑(H)
k(G, H)
3
Talk Structure
1 Explict vs. Implicit Graph Kernels, IEEE ICDM 2014
2 Fast Kernels for Graphs with Continuous Labels, IEEE ICDM 2016
3 Graph Kernels Based on Optimal Assignments, NIPS 2016
4 Outlook/What’s next?
4
Part I: Explicit vs. Implicit Graph Kernels
Challenge
Investigate the benefits of explicit and implicit graph kernels.
N. Kriege, M. Neumann, K. Kersting, and P. Mutzel. “Explicit versus
Implicit Graph Feature Maps: A Computational Phase Transition for
Walk Kernels”. In: IEEE International Conference on Data Mining.
2014, pp. 881–886
N. M. Kriege, M. Neumann, C. Morris, K. Kersting, and P. Mutzel. “A
Unifying View of Explicit and Implicit Feature Maps for Structured
Data: Systematic Studies of Graph Kernels”. In: CoRR abs/1703.00676
(2017). url: http://arxiv.org/abs/1703.00676
5
Part I: Explicit vs. Implicit Graph Kernels
𝜑 Cont. Labels Run time
Random Walk [Gärtner et al., 2003] IM  𝒪(n2𝜔
)
Shortest-Path [Borgwardt et al., 2005] IM  𝒪(n4
)
Subgraph Matching [Kriege, Mutzel, 2012] IM  𝒪(kn2k+2
)
GraphHopper [Feragen et al., 2013] IM  𝒪(n2
m)
Graphlet [Shervashidze et al., 2009] EX 
NSPDK [Costa et al., 2010] EX 
Weisfeiler-Lehman [Shervashidze et al., 2011] EX  𝒪(hm)
Propagation [Neumann et al., 2016] EX 
Implicit vs. Explicit
• Implicit Kernels: do not scale, extendable to continuous labels
• Explicit Kernels: do scale, only discrete labels
6
Part I: Explicit vs. Implicit Graph Kernels
Challenge
Investigate the benefits of explicit and implicit graph kernels.
7
Part I: Explicit vs. Implicit Graph Kernels
Challenge
Investigate the benefits of explicit and implicit graph kernels.
Contribution
• Conditions under which the computation of a
finite-dimensional explicit mapping is possible
7
Part I: Explicit vs. Implicit Graph Kernels
Challenge
Investigate the benefits of explicit and implicit graph kernels.
Contribution
• Conditions under which the computation of a
finite-dimensional explicit mapping is possible
• Explicit feature maps for convolution kernels
7
Part I: Explicit vs. Implicit Graph Kernels
Challenge
Investigate the benefits of explicit and implicit graph kernels.
Contribution
• Conditions under which the computation of a
finite-dimensional explicit mapping is possible
• Explicit feature maps for convolution kernels
• Weighted vertex kernels: derived approximate finite-dimensional
explicit feature maps
7
Part I: Explicit vs. Implicit Graph Kernels
Challenge
Investigate the benefits of explicit and implicit graph kernels.
Contribution
• Conditions under which the computation of a
finite-dimensional explicit mapping is possible
• Explicit feature maps for convolution kernels
• Weighted vertex kernels: derived approximate finite-dimensional
explicit feature maps
• Validated theoretical results in experimental study
7
Part I: Explicit vs. Implicit Graph Kernels
implicit
explicit
100
150
200
250
300
Data set size
0
1020
30
40
50
60
Label diversity
0
2
4
6
8
10
Runtime [s]
Experimental Results
Discrete Labels: explicit feature maps outperform implicit kernels
(for most kernels and benchmark data sets)
8
Part I: Explicit vs. Implicit Graph Kernels
implicit
explicit
100
150
200
250
300
Data set size
0
1020
30
40
50
60
Label diversity
0
2
4
6
8
10
Runtime [s]
Experimental Results
Discrete Labels: explicit feature maps outperform implicit kernels
(for most kernels and benchmark data sets)
Continuous Labels: approximation by explicit feature maps not
competitive for complex kernels
8
Part II: Hash Graph Kernel Framework
Challenge
Design fast, explicit graph kernels that can handle continuous
labels.
C. Morris, N. M. Kriege, K. Kersting, and P. Mutzel. “Faster Kernel for
Graphs with Continuous Attributes via Hashing”. In: IEEE
International Conference on Data Mining. 2016, pp. 1095–1100
[ 1.2
0.3 ]
[ 9.1
0.9 ]
[ 1.6
0.7 ]
[ 5.2
1.0 ]
[ 5.1
0.2 ]
[ 1.0
0.2 ]
9
Part II: Hash Graph Kernel Framework
Challenge
Design fast, explicit graph kernels that can handle continuous
labels.
𝜑 Cont. Labels Run time
Random Walk [Gärtner et al., 2003] IM  𝒪(n2𝜔
)
Shortest-Path [Borgwardt et al., 2005] IM  𝒪(n4
)
Subgraph Matching [Kriege, Mutzel, 2012] IM  𝒪(kn2k+2
)
GraphHopper [Feragen et al., 2013] IM  𝒪(n2
m)
Graphlet [Shervashidze et al., 2009] EX 
NSPDK [Costa et al., 2010] EX 
Weisfeiler-Lehman [Shervashidze et al., 2011] EX  𝒪(hm)
Propagation [Neumann et al., 2016] EX 
HGK Framework [Morris et al., 2016] EX  Linear in BK
10
Part II: Hash Graph Kernel Framework
(G, a)
(G, l1)
(G, l2)
Hash
φ(G, l1)
φ(G, l2)
1/I[φ(G,l1),...,φ(G,lI)]
Feat. Vectors
(G, lI) φ(G, lI)
11
Part II: Hash Graph Kernel Framework
Contribution: Hash Graph Kernel Framework
• Use explicit instead of implicit kernels, i.e., avoid kernel trick!
12
Part II: Hash Graph Kernel Framework
Contribution: Hash Graph Kernel Framework
• Use explicit instead of implicit kernels, i.e., avoid kernel trick!
• Applicable to a wide range of graph kernel functions
(Weisfeiler-Lehman, Shortest-Path, Graphlet, ...)
12
Part II: Hash Graph Kernel Framework
Contribution: Hash Graph Kernel Framework
• Use explicit instead of implicit kernels, i.e., avoid kernel trick!
• Applicable to a wide range of graph kernel functions
(Weisfeiler-Lehman, Shortest-Path, Graphlet, ...)
• Theoretical approximation bounds
12
Part II: Hash Graph Kernel Framework
Contribution: Hash Graph Kernel Framework
• Use explicit instead of implicit kernels, i.e., avoid kernel trick!
• Applicable to a wide range of graph kernel functions
(Weisfeiler-Lehman, Shortest-Path, Graphlet, ...)
• Theoretical approximation bounds
• State-of-the-art classification accuracies but orders of
magnitude faster than implicit kernels
12
Part II: Hash Graph Kernel Framework
Contribution: Hash Graph Kernel Framework
• Use explicit instead of implicit kernels, i.e., avoid kernel trick!
• Applicable to a wide range of graph kernel functions
(Weisfeiler-Lehman, Shortest-Path, Graphlet, ...)
• Theoretical approximation bounds
• State-of-the-art classification accuracies but orders of
magnitude faster than implicit kernels
Question
Is there no benefit from employing the kernel trick at all on the
graph domain?
12
Part III: Positive-semidefinite Optimal Assignments
Challenge
Design valid graph kernel that is based on optimal assignments.
X Y
a
a
a
b
c
a
b
b
c
c
N. M. Kriege, Giscard. P.-L., and R. C. Wilson. “On Valid Optimal
Assignment Kernels and Applications to Graph Classification”. In:
Advances in Neural Information Processing Systems. 2016,
pp. 1615–1623
13
Part III: Positive-semidefinite Optimal Assignments
Intuition
Optimal Assignments are a “natural” measure of similarity.
Definition (Optimal Assignment Kernel)
Let ℬ(X, Y) be the bijections between X, Y in [𝒮]n
, the optimal
assignment kernel on [𝒮]n
is defined as
Kk
ℬ(X, Y) = max
B∈ℬ(X,Y)
W(B), where W(B) =
∑︁
(x,y)∈B
k(x, y)
and k is a base kernel on 𝒮.
14
Part III: Positive-semidefinite Optimal Assignments
Previous Work:
• Optimal assignment kernels for attributed molecular graphs
[Fröhlich, Wegner, Sieker, Zell, 2005], ICML
• The optimal assignment kernel is not positive definite
[Vert, 2008], CoRR, abs/0801.4061
Problem
Optimal assignments yield indefinite functions.
15
Part III: Positive-semidefinite Optimal Assignments
Definition (Strong Kernel)
A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳
k(x, y) ≥ min{k(x, z), k(z, y)}.
16
Part III: Positive-semidefinite Optimal Assignments
Definition (Strong Kernel)
A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳
k(x, y) ≥ min{k(x, z), k(z, y)}.
a b c
a 4 3 1
b 3 5 1
c 1 1 2
• every object is most similar to itself
16
Part III: Positive-semidefinite Optimal Assignments
Definition (Strong Kernel)
A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳
k(x, y) ≥ min{k(x, z), k(z, y)}.
a b c
a 4 3 1
b 3 5 1
c 1 1 2
• every object is most similar to itself
• strong kernels are indeed PSD
16
Part III: Positive-semidefinite Optimal Assignments
Definition (Strong Kernel)
A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳
k(x, y) ≥ min{k(x, z), k(z, y)}.
a b c
a 4 3 1
b 3 5 1
c 1 1 2
• every object is most similar to itself
• strong kernels are indeed PSD
• strong kernels give rise to hierarchies
16
Part III: Positive-semidefinite Optimal Assignments
Definition (Strong Kernel)
A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳
k(x, y) ≥ min{k(x, z), k(z, y)}.
a b c
a 4 3 1
b 3 5 1
c 1 1 2
• every object is most similar to itself
• strong kernels are indeed PSD
• strong kernels give rise to hierarchies
Contribution
• Strong base kernels that guarantee PSD optimal assignment
kernels
16
Part III: Positive-semidefinite Optimal Assignments
Definition (Strong Kernel)
A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳
k(x, y) ≥ min{k(x, z), k(z, y)}.
a b c
a 4 3 1
b 3 5 1
c 1 1 2
• every object is most similar to itself
• strong kernels are indeed PSD
• strong kernels give rise to hierarchies
Contribution
• Strong base kernels that guarantee PSD optimal assignment
kernels
• Linear time computation of optimal assignment kernels
16
Part III: Positive-semidefinite Optimal Assignments
Definition (Strong Kernel)
A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳
k(x, y) ≥ min{k(x, z), k(z, y)}.
a b c
a 4 3 1
b 3 5 1
c 1 1 2
• every object is most similar to itself
• strong kernels are indeed PSD
• strong kernels give rise to hierarchies
Contribution
• Strong base kernels that guarantee PSD optimal assignment
kernels
• Linear time computation of optimal assignment kernels
• Weisfeiler-Lehman optimal assignment kernels 16
Outlook/What’s next?
Classical Graph Kernels
C. Morris, K. Kersting, and M. Mutzel. “Glocalized Weisfeiler-Lehman
Graph Kernels: Global-Local Feature Maps of Graphs”. In: IEEE
International Conference on Data Mining. 2017
17
Outlook/What’s next?
Classical Graph Kernels
C. Morris, K. Kersting, and M. Mutzel. “Glocalized Weisfeiler-Lehman
Graph Kernels: Global-Local Feature Maps of Graphs”. In: IEEE
International Conference on Data Mining. 2017
Optimization Based Graph Feature Maps
Classical:
Feature Engineering
Phase I
Classifier
Phase II
17
Outlook/What’s next?
Classical Graph Kernels
C. Morris, K. Kersting, and M. Mutzel. “Glocalized Weisfeiler-Lehman
Graph Kernels: Global-Local Feature Maps of Graphs”. In: IEEE
International Conference on Data Mining. 2017
Optimization Based Graph Feature Maps
Classical:
Feature Engineering
Phase I
Classifier
Phase II
End-to-End:
Feature Engineering + Classifier
Phase I + Phase II
Optimize Parameters
17
Conclusion
1 Explicit vs. Implicit Kernels
2 Hash Graph Kernel Framework
3 Valid Kernels from Optimal Assignments
Collection of Graph Classification Benchmarks
graphkernels.cs.tu-dortmund.de
18
References I
Kriege, N. M., Giscard. P.-L., and R. C. Wilson. “On Valid Optimal
Assignment Kernels and Applications to Graph Classification”. In:
Advances in Neural Information Processing Systems. 2016,
pp. 1615–1623.
Kriege, N. M. et al. “A Unifying View of Explicit and Implicit Feature
Maps for Structured Data: Systematic Studies of Graph Kernels”. In:
CoRR abs/1703.00676 (2017). url:
http://arxiv.org/abs/1703.00676.
Kriege, N. et al. “Explicit versus Implicit Graph Feature Maps: A
Computational Phase Transition for Walk Kernels”. In: IEEE
International Conference on Data Mining. 2014, pp. 881–886.
Morris, C., K. Kersting, and M. Mutzel. “Glocalized Weisfeiler-Lehman
Graph Kernels: Global-Local Feature Maps of Graphs”. In: IEEE
International Conference on Data Mining. 2017.
19
References II
Morris, C. et al. “Faster Kernel for Graphs with Continuous Attributes
via Hashing”. In: IEEE International Conference on Data Mining.
2016, pp. 1095–1100.
20

Mais conteúdo relacionado

Mais procurados

Lucas Theis - Compressing Images with Neural Networks - Creative AI meetup
Lucas Theis - Compressing Images with Neural Networks - Creative AI meetupLucas Theis - Compressing Images with Neural Networks - Creative AI meetup
Lucas Theis - Compressing Images with Neural Networks - Creative AI meetupLuba Elliott
 
Graph Convolutional Neural Networks
Graph Convolutional Neural Networks Graph Convolutional Neural Networks
Graph Convolutional Neural Networks 신동 강
 
A short and naive introduction to using network in prediction models
A short and naive introduction to using network in prediction modelsA short and naive introduction to using network in prediction models
A short and naive introduction to using network in prediction modelstuxette
 
Webinar on Graph Neural Networks
Webinar on Graph Neural NetworksWebinar on Graph Neural Networks
Webinar on Graph Neural NetworksLucaCrociani1
 
Spectral clustering Tutorial
Spectral clustering TutorialSpectral clustering Tutorial
Spectral clustering TutorialZitao Liu
 
IJCAI13 Paper review: Large-scale spectral clustering on graphs
IJCAI13 Paper review: Large-scale spectral clustering on graphsIJCAI13 Paper review: Large-scale spectral clustering on graphs
IJCAI13 Paper review: Large-scale spectral clustering on graphsAkisato Kimura
 
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...Artem Lutov
 
Spectral clustering with motifs and higher-order structures
Spectral clustering with motifs and higher-order structuresSpectral clustering with motifs and higher-order structures
Spectral clustering with motifs and higher-order structuresDavid Gleich
 
Notes on Spectral Clustering
Notes on Spectral ClusteringNotes on Spectral Clustering
Notes on Spectral ClusteringDavide Eynard
 
Object Detection Beyond Mask R-CNN and RetinaNet III
Object Detection Beyond Mask R-CNN and RetinaNet IIIObject Detection Beyond Mask R-CNN and RetinaNet III
Object Detection Beyond Mask R-CNN and RetinaNet IIIWanjin Yu
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesFellowship at Vodafone FutureLab
 
Training and Inference for Deep Gaussian Processes
Training and Inference for Deep Gaussian ProcessesTraining and Inference for Deep Gaussian Processes
Training and Inference for Deep Gaussian ProcessesKeyon Vafa
 
Clustering techniques
Clustering techniquesClustering techniques
Clustering techniquestalktoharry
 
Graph Based Clustering
Graph Based ClusteringGraph Based Clustering
Graph Based ClusteringSSA KPI
 
010_20160216_Variational Gaussian Process
010_20160216_Variational Gaussian Process010_20160216_Variational Gaussian Process
010_20160216_Variational Gaussian ProcessHa Phuong
 
JOSA TechTalks - Machine Learning on Graph-Structured Data
JOSA TechTalks - Machine Learning on Graph-Structured DataJOSA TechTalks - Machine Learning on Graph-Structured Data
JOSA TechTalks - Machine Learning on Graph-Structured DataJordan Open Source Association
 
PixelGAN Autoencoders
  PixelGAN Autoencoders  PixelGAN Autoencoders
PixelGAN AutoencodersMLReview
 

Mais procurados (20)

Lucas Theis - Compressing Images with Neural Networks - Creative AI meetup
Lucas Theis - Compressing Images with Neural Networks - Creative AI meetupLucas Theis - Compressing Images with Neural Networks - Creative AI meetup
Lucas Theis - Compressing Images with Neural Networks - Creative AI meetup
 
Graph Convolutional Neural Networks
Graph Convolutional Neural Networks Graph Convolutional Neural Networks
Graph Convolutional Neural Networks
 
A short and naive introduction to using network in prediction models
A short and naive introduction to using network in prediction modelsA short and naive introduction to using network in prediction models
A short and naive introduction to using network in prediction models
 
Webinar on Graph Neural Networks
Webinar on Graph Neural NetworksWebinar on Graph Neural Networks
Webinar on Graph Neural Networks
 
Spectral clustering Tutorial
Spectral clustering TutorialSpectral clustering Tutorial
Spectral clustering Tutorial
 
IJCAI13 Paper review: Large-scale spectral clustering on graphs
IJCAI13 Paper review: Large-scale spectral clustering on graphsIJCAI13 Paper review: Large-scale spectral clustering on graphs
IJCAI13 Paper review: Large-scale spectral clustering on graphs
 
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
 
Spectral clustering with motifs and higher-order structures
Spectral clustering with motifs and higher-order structuresSpectral clustering with motifs and higher-order structures
Spectral clustering with motifs and higher-order structures
 
Notes on Spectral Clustering
Notes on Spectral ClusteringNotes on Spectral Clustering
Notes on Spectral Clustering
 
Object Detection Beyond Mask R-CNN and RetinaNet III
Object Detection Beyond Mask R-CNN and RetinaNet IIIObject Detection Beyond Mask R-CNN and RetinaNet III
Object Detection Beyond Mask R-CNN and RetinaNet III
 
CSMR11b.ppt
CSMR11b.pptCSMR11b.ppt
CSMR11b.ppt
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network Approaches
 
Training and Inference for Deep Gaussian Processes
Training and Inference for Deep Gaussian ProcessesTraining and Inference for Deep Gaussian Processes
Training and Inference for Deep Gaussian Processes
 
Clustering techniques
Clustering techniquesClustering techniques
Clustering techniques
 
Neural Doodle
Neural DoodleNeural Doodle
Neural Doodle
 
Graph Based Clustering
Graph Based ClusteringGraph Based Clustering
Graph Based Clustering
 
010_20160216_Variational Gaussian Process
010_20160216_Variational Gaussian Process010_20160216_Variational Gaussian Process
010_20160216_Variational Gaussian Process
 
Sandia Fast Matmul
Sandia Fast MatmulSandia Fast Matmul
Sandia Fast Matmul
 
JOSA TechTalks - Machine Learning on Graph-Structured Data
JOSA TechTalks - Machine Learning on Graph-Structured DataJOSA TechTalks - Machine Learning on Graph-Structured Data
JOSA TechTalks - Machine Learning on Graph-Structured Data
 
PixelGAN Autoencoders
  PixelGAN Autoencoders  PixelGAN Autoencoders
PixelGAN Autoencoders
 

Semelhante a Recent Advances in Kernel-Based Graph Classification

IndexedRDD: Efficeint Fine-Grained Updates for RDD's-(Ankur Dave, UC Berkeley)
IndexedRDD: Efficeint Fine-Grained Updates for RDD's-(Ankur Dave, UC Berkeley)IndexedRDD: Efficeint Fine-Grained Updates for RDD's-(Ankur Dave, UC Berkeley)
IndexedRDD: Efficeint Fine-Grained Updates for RDD's-(Ankur Dave, UC Berkeley)Spark Summit
 
Deep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistryDeep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistryKenta Oono
 
Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI Projects
Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI ProjectsDiscovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI Projects
Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI ProjectsWee Hyong Tok
 
ImageNet classification with deep convolutional neural networks(2012)
ImageNet classification with deep convolutional neural networks(2012)ImageNet classification with deep convolutional neural networks(2012)
ImageNet classification with deep convolutional neural networks(2012)WoochulShin10
 
Instance Based Learning in Machine Learning
Instance Based Learning in Machine LearningInstance Based Learning in Machine Learning
Instance Based Learning in Machine LearningPavithra Thippanaik
 
convolutional_neural_networks in deep learning
convolutional_neural_networks in deep learningconvolutional_neural_networks in deep learning
convolutional_neural_networks in deep learningssusere5ddd6
 
Neural Networks: Support Vector machines
Neural Networks: Support Vector machinesNeural Networks: Support Vector machines
Neural Networks: Support Vector machinesMostafa G. M. Mostafa
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningCastLabKAIST
 
Architecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IArchitecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IWanjin Yu
 
Web-Scale Graph Analytics with Apache® Spark™
Web-Scale Graph Analytics with Apache® Spark™Web-Scale Graph Analytics with Apache® Spark™
Web-Scale Graph Analytics with Apache® Spark™Databricks
 
GENERALIZED LEGENDRE POLYNOMIALS FOR SUPPORT VECTOR MACHINES (SVMS) CLASSIFIC...
GENERALIZED LEGENDRE POLYNOMIALS FOR SUPPORT VECTOR MACHINES (SVMS) CLASSIFIC...GENERALIZED LEGENDRE POLYNOMIALS FOR SUPPORT VECTOR MACHINES (SVMS) CLASSIFIC...
GENERALIZED LEGENDRE POLYNOMIALS FOR SUPPORT VECTOR MACHINES (SVMS) CLASSIFIC...IJNSA Journal
 
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at GoogleDataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at GoogleHakka Labs
 
Beyond Map/Reduce: Getting Creative With Parallel Processing
Beyond Map/Reduce: Getting Creative With Parallel ProcessingBeyond Map/Reduce: Getting Creative With Parallel Processing
Beyond Map/Reduce: Getting Creative With Parallel ProcessingEd Kohlwey
 
Svm map reduce_slides
Svm map reduce_slidesSvm map reduce_slides
Svm map reduce_slidesSara Asher
 
[Paper Reading] Attention is All You Need
[Paper Reading] Attention is All You Need[Paper Reading] Attention is All You Need
[Paper Reading] Attention is All You NeedDaiki Tanaka
 
Advanced Data Structures 2006
Advanced Data Structures 2006Advanced Data Structures 2006
Advanced Data Structures 2006Sanjay Goel
 
Density based methods
Density based methodsDensity based methods
Density based methodsSVijaylakshmi
 

Semelhante a Recent Advances in Kernel-Based Graph Classification (20)

IndexedRDD: Efficeint Fine-Grained Updates for RDD's-(Ankur Dave, UC Berkeley)
IndexedRDD: Efficeint Fine-Grained Updates for RDD's-(Ankur Dave, UC Berkeley)IndexedRDD: Efficeint Fine-Grained Updates for RDD's-(Ankur Dave, UC Berkeley)
IndexedRDD: Efficeint Fine-Grained Updates for RDD's-(Ankur Dave, UC Berkeley)
 
Deep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistryDeep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistry
 
Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI Projects
Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI ProjectsDiscovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI Projects
Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI Projects
 
ImageNet classification with deep convolutional neural networks(2012)
ImageNet classification with deep convolutional neural networks(2012)ImageNet classification with deep convolutional neural networks(2012)
ImageNet classification with deep convolutional neural networks(2012)
 
Instance Based Learning in Machine Learning
Instance Based Learning in Machine LearningInstance Based Learning in Machine Learning
Instance Based Learning in Machine Learning
 
convolutional_neural_networks in deep learning
convolutional_neural_networks in deep learningconvolutional_neural_networks in deep learning
convolutional_neural_networks in deep learning
 
Neural Networks: Support Vector machines
Neural Networks: Support Vector machinesNeural Networks: Support Vector machines
Neural Networks: Support Vector machines
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine Learning
 
Cd32504509
Cd32504509Cd32504509
Cd32504509
 
Cd32504509
Cd32504509Cd32504509
Cd32504509
 
[ppt]
[ppt][ppt]
[ppt]
 
Architecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IArchitecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks I
 
Web-Scale Graph Analytics with Apache® Spark™
Web-Scale Graph Analytics with Apache® Spark™Web-Scale Graph Analytics with Apache® Spark™
Web-Scale Graph Analytics with Apache® Spark™
 
GENERALIZED LEGENDRE POLYNOMIALS FOR SUPPORT VECTOR MACHINES (SVMS) CLASSIFIC...
GENERALIZED LEGENDRE POLYNOMIALS FOR SUPPORT VECTOR MACHINES (SVMS) CLASSIFIC...GENERALIZED LEGENDRE POLYNOMIALS FOR SUPPORT VECTOR MACHINES (SVMS) CLASSIFIC...
GENERALIZED LEGENDRE POLYNOMIALS FOR SUPPORT VECTOR MACHINES (SVMS) CLASSIFIC...
 
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at GoogleDataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
 
Beyond Map/Reduce: Getting Creative With Parallel Processing
Beyond Map/Reduce: Getting Creative With Parallel ProcessingBeyond Map/Reduce: Getting Creative With Parallel Processing
Beyond Map/Reduce: Getting Creative With Parallel Processing
 
Svm map reduce_slides
Svm map reduce_slidesSvm map reduce_slides
Svm map reduce_slides
 
[Paper Reading] Attention is All You Need
[Paper Reading] Attention is All You Need[Paper Reading] Attention is All You Need
[Paper Reading] Attention is All You Need
 
Advanced Data Structures 2006
Advanced Data Structures 2006Advanced Data Structures 2006
Advanced Data Structures 2006
 
Density based methods
Density based methodsDensity based methods
Density based methods
 

Último

TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...ssifa0344
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoSérgio Sacani
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)Areesha Ahmad
 
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINChromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINsankalpkumarsahoo174
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000Sapana Sha
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTSérgio Sacani
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfSumit Kumar yadav
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsSérgio Sacani
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRDelhi Call girls
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡anilsa9823
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfSumit Kumar yadav
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bSérgio Sacani
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
fundamental of entomology all in one topics of entomology
fundamental of entomology all in one topics of entomologyfundamental of entomology all in one topics of entomology
fundamental of entomology all in one topics of entomologyDrAnita Sharma
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...anilsa9823
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSSLeenakshiTyagi
 

Último (20)

TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on Io
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINChromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOST
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdf
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdf
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
fundamental of entomology all in one topics of entomology
fundamental of entomology all in one topics of entomologyfundamental of entomology all in one topics of entomology
fundamental of entomology all in one topics of entomology
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 
The Philosophy of Science
The Philosophy of ScienceThe Philosophy of Science
The Philosophy of Science
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSS
 

Recent Advances in Kernel-Based Graph Classification

  • 1. Recent Advances in Kernel-Based Graph Classification ECML PKDD 2017, Nectar Track Nils Kriege, Christopher Morris June 20, 2017 TU Dortmund University, Algorithm Engineering Group
  • 2. Motivation Question How similar are two graphs? (a) Sildenafil (b) Vardenafil 1
  • 3. High-level View: Supervised Graph Classification ⊆ H φ 2
  • 4. Primer on Graph Kernels Question How similar are two graphs? Definition (Graph Kernel) Let 𝒢 be a non-empty set of graphs and let k: 𝒢 × 𝒢 → R. Then k is a graph kernel if there is a real Hilbert space ℋ and a feature map 𝜑: 𝒢 → ℋ such that k(G, H) = ⟨𝜑(G), 𝜑(H)⟩. Explicit vs. Implicit Exp. (EX) Imp. (IM) G H Inner Product PSD function 𝜑(G) 𝜑(H) k(G, H) 3
  • 5. Talk Structure 1 Explict vs. Implicit Graph Kernels, IEEE ICDM 2014 2 Fast Kernels for Graphs with Continuous Labels, IEEE ICDM 2016 3 Graph Kernels Based on Optimal Assignments, NIPS 2016 4 Outlook/What’s next? 4
  • 6. Part I: Explicit vs. Implicit Graph Kernels Challenge Investigate the benefits of explicit and implicit graph kernels. N. Kriege, M. Neumann, K. Kersting, and P. Mutzel. “Explicit versus Implicit Graph Feature Maps: A Computational Phase Transition for Walk Kernels”. In: IEEE International Conference on Data Mining. 2014, pp. 881–886 N. M. Kriege, M. Neumann, C. Morris, K. Kersting, and P. Mutzel. “A Unifying View of Explicit and Implicit Feature Maps for Structured Data: Systematic Studies of Graph Kernels”. In: CoRR abs/1703.00676 (2017). url: http://arxiv.org/abs/1703.00676 5
  • 7. Part I: Explicit vs. Implicit Graph Kernels 𝜑 Cont. Labels Run time Random Walk [Gärtner et al., 2003] IM 𝒪(n2𝜔 ) Shortest-Path [Borgwardt et al., 2005] IM 𝒪(n4 ) Subgraph Matching [Kriege, Mutzel, 2012] IM 𝒪(kn2k+2 ) GraphHopper [Feragen et al., 2013] IM 𝒪(n2 m) Graphlet [Shervashidze et al., 2009] EX NSPDK [Costa et al., 2010] EX Weisfeiler-Lehman [Shervashidze et al., 2011] EX 𝒪(hm) Propagation [Neumann et al., 2016] EX Implicit vs. Explicit • Implicit Kernels: do not scale, extendable to continuous labels • Explicit Kernels: do scale, only discrete labels 6
  • 8. Part I: Explicit vs. Implicit Graph Kernels Challenge Investigate the benefits of explicit and implicit graph kernels. 7
  • 9. Part I: Explicit vs. Implicit Graph Kernels Challenge Investigate the benefits of explicit and implicit graph kernels. Contribution • Conditions under which the computation of a finite-dimensional explicit mapping is possible 7
  • 10. Part I: Explicit vs. Implicit Graph Kernels Challenge Investigate the benefits of explicit and implicit graph kernels. Contribution • Conditions under which the computation of a finite-dimensional explicit mapping is possible • Explicit feature maps for convolution kernels 7
  • 11. Part I: Explicit vs. Implicit Graph Kernels Challenge Investigate the benefits of explicit and implicit graph kernels. Contribution • Conditions under which the computation of a finite-dimensional explicit mapping is possible • Explicit feature maps for convolution kernels • Weighted vertex kernels: derived approximate finite-dimensional explicit feature maps 7
  • 12. Part I: Explicit vs. Implicit Graph Kernels Challenge Investigate the benefits of explicit and implicit graph kernels. Contribution • Conditions under which the computation of a finite-dimensional explicit mapping is possible • Explicit feature maps for convolution kernels • Weighted vertex kernels: derived approximate finite-dimensional explicit feature maps • Validated theoretical results in experimental study 7
  • 13. Part I: Explicit vs. Implicit Graph Kernels implicit explicit 100 150 200 250 300 Data set size 0 1020 30 40 50 60 Label diversity 0 2 4 6 8 10 Runtime [s] Experimental Results Discrete Labels: explicit feature maps outperform implicit kernels (for most kernels and benchmark data sets) 8
  • 14. Part I: Explicit vs. Implicit Graph Kernels implicit explicit 100 150 200 250 300 Data set size 0 1020 30 40 50 60 Label diversity 0 2 4 6 8 10 Runtime [s] Experimental Results Discrete Labels: explicit feature maps outperform implicit kernels (for most kernels and benchmark data sets) Continuous Labels: approximation by explicit feature maps not competitive for complex kernels 8
  • 15. Part II: Hash Graph Kernel Framework Challenge Design fast, explicit graph kernels that can handle continuous labels. C. Morris, N. M. Kriege, K. Kersting, and P. Mutzel. “Faster Kernel for Graphs with Continuous Attributes via Hashing”. In: IEEE International Conference on Data Mining. 2016, pp. 1095–1100 [ 1.2 0.3 ] [ 9.1 0.9 ] [ 1.6 0.7 ] [ 5.2 1.0 ] [ 5.1 0.2 ] [ 1.0 0.2 ] 9
  • 16. Part II: Hash Graph Kernel Framework Challenge Design fast, explicit graph kernels that can handle continuous labels. 𝜑 Cont. Labels Run time Random Walk [Gärtner et al., 2003] IM 𝒪(n2𝜔 ) Shortest-Path [Borgwardt et al., 2005] IM 𝒪(n4 ) Subgraph Matching [Kriege, Mutzel, 2012] IM 𝒪(kn2k+2 ) GraphHopper [Feragen et al., 2013] IM 𝒪(n2 m) Graphlet [Shervashidze et al., 2009] EX NSPDK [Costa et al., 2010] EX Weisfeiler-Lehman [Shervashidze et al., 2011] EX 𝒪(hm) Propagation [Neumann et al., 2016] EX HGK Framework [Morris et al., 2016] EX Linear in BK 10
  • 17. Part II: Hash Graph Kernel Framework (G, a) (G, l1) (G, l2) Hash φ(G, l1) φ(G, l2) 1/I[φ(G,l1),...,φ(G,lI)] Feat. Vectors (G, lI) φ(G, lI) 11
  • 18. Part II: Hash Graph Kernel Framework Contribution: Hash Graph Kernel Framework • Use explicit instead of implicit kernels, i.e., avoid kernel trick! 12
  • 19. Part II: Hash Graph Kernel Framework Contribution: Hash Graph Kernel Framework • Use explicit instead of implicit kernels, i.e., avoid kernel trick! • Applicable to a wide range of graph kernel functions (Weisfeiler-Lehman, Shortest-Path, Graphlet, ...) 12
  • 20. Part II: Hash Graph Kernel Framework Contribution: Hash Graph Kernel Framework • Use explicit instead of implicit kernels, i.e., avoid kernel trick! • Applicable to a wide range of graph kernel functions (Weisfeiler-Lehman, Shortest-Path, Graphlet, ...) • Theoretical approximation bounds 12
  • 21. Part II: Hash Graph Kernel Framework Contribution: Hash Graph Kernel Framework • Use explicit instead of implicit kernels, i.e., avoid kernel trick! • Applicable to a wide range of graph kernel functions (Weisfeiler-Lehman, Shortest-Path, Graphlet, ...) • Theoretical approximation bounds • State-of-the-art classification accuracies but orders of magnitude faster than implicit kernels 12
  • 22. Part II: Hash Graph Kernel Framework Contribution: Hash Graph Kernel Framework • Use explicit instead of implicit kernels, i.e., avoid kernel trick! • Applicable to a wide range of graph kernel functions (Weisfeiler-Lehman, Shortest-Path, Graphlet, ...) • Theoretical approximation bounds • State-of-the-art classification accuracies but orders of magnitude faster than implicit kernels Question Is there no benefit from employing the kernel trick at all on the graph domain? 12
  • 23. Part III: Positive-semidefinite Optimal Assignments Challenge Design valid graph kernel that is based on optimal assignments. X Y a a a b c a b b c c N. M. Kriege, Giscard. P.-L., and R. C. Wilson. “On Valid Optimal Assignment Kernels and Applications to Graph Classification”. In: Advances in Neural Information Processing Systems. 2016, pp. 1615–1623 13
  • 24. Part III: Positive-semidefinite Optimal Assignments Intuition Optimal Assignments are a “natural” measure of similarity. Definition (Optimal Assignment Kernel) Let ℬ(X, Y) be the bijections between X, Y in [𝒮]n , the optimal assignment kernel on [𝒮]n is defined as Kk ℬ(X, Y) = max B∈ℬ(X,Y) W(B), where W(B) = ∑︁ (x,y)∈B k(x, y) and k is a base kernel on 𝒮. 14
  • 25. Part III: Positive-semidefinite Optimal Assignments Previous Work: • Optimal assignment kernels for attributed molecular graphs [Fröhlich, Wegner, Sieker, Zell, 2005], ICML • The optimal assignment kernel is not positive definite [Vert, 2008], CoRR, abs/0801.4061 Problem Optimal assignments yield indefinite functions. 15
  • 26. Part III: Positive-semidefinite Optimal Assignments Definition (Strong Kernel) A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳 k(x, y) ≥ min{k(x, z), k(z, y)}. 16
  • 27. Part III: Positive-semidefinite Optimal Assignments Definition (Strong Kernel) A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳 k(x, y) ≥ min{k(x, z), k(z, y)}. a b c a 4 3 1 b 3 5 1 c 1 1 2 • every object is most similar to itself 16
  • 28. Part III: Positive-semidefinite Optimal Assignments Definition (Strong Kernel) A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳 k(x, y) ≥ min{k(x, z), k(z, y)}. a b c a 4 3 1 b 3 5 1 c 1 1 2 • every object is most similar to itself • strong kernels are indeed PSD 16
  • 29. Part III: Positive-semidefinite Optimal Assignments Definition (Strong Kernel) A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳 k(x, y) ≥ min{k(x, z), k(z, y)}. a b c a 4 3 1 b 3 5 1 c 1 1 2 • every object is most similar to itself • strong kernels are indeed PSD • strong kernels give rise to hierarchies 16
  • 30. Part III: Positive-semidefinite Optimal Assignments Definition (Strong Kernel) A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳 k(x, y) ≥ min{k(x, z), k(z, y)}. a b c a 4 3 1 b 3 5 1 c 1 1 2 • every object is most similar to itself • strong kernels are indeed PSD • strong kernels give rise to hierarchies Contribution • Strong base kernels that guarantee PSD optimal assignment kernels 16
  • 31. Part III: Positive-semidefinite Optimal Assignments Definition (Strong Kernel) A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳 k(x, y) ≥ min{k(x, z), k(z, y)}. a b c a 4 3 1 b 3 5 1 c 1 1 2 • every object is most similar to itself • strong kernels are indeed PSD • strong kernels give rise to hierarchies Contribution • Strong base kernels that guarantee PSD optimal assignment kernels • Linear time computation of optimal assignment kernels 16
  • 32. Part III: Positive-semidefinite Optimal Assignments Definition (Strong Kernel) A function k : 𝒳 × 𝒳 → R is a strong kernel if for all x, y, z ∈ 𝒳 k(x, y) ≥ min{k(x, z), k(z, y)}. a b c a 4 3 1 b 3 5 1 c 1 1 2 • every object is most similar to itself • strong kernels are indeed PSD • strong kernels give rise to hierarchies Contribution • Strong base kernels that guarantee PSD optimal assignment kernels • Linear time computation of optimal assignment kernels • Weisfeiler-Lehman optimal assignment kernels 16
  • 33. Outlook/What’s next? Classical Graph Kernels C. Morris, K. Kersting, and M. Mutzel. “Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs”. In: IEEE International Conference on Data Mining. 2017 17
  • 34. Outlook/What’s next? Classical Graph Kernels C. Morris, K. Kersting, and M. Mutzel. “Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs”. In: IEEE International Conference on Data Mining. 2017 Optimization Based Graph Feature Maps Classical: Feature Engineering Phase I Classifier Phase II 17
  • 35. Outlook/What’s next? Classical Graph Kernels C. Morris, K. Kersting, and M. Mutzel. “Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs”. In: IEEE International Conference on Data Mining. 2017 Optimization Based Graph Feature Maps Classical: Feature Engineering Phase I Classifier Phase II End-to-End: Feature Engineering + Classifier Phase I + Phase II Optimize Parameters 17
  • 36. Conclusion 1 Explicit vs. Implicit Kernels 2 Hash Graph Kernel Framework 3 Valid Kernels from Optimal Assignments Collection of Graph Classification Benchmarks graphkernels.cs.tu-dortmund.de 18
  • 37. References I Kriege, N. M., Giscard. P.-L., and R. C. Wilson. “On Valid Optimal Assignment Kernels and Applications to Graph Classification”. In: Advances in Neural Information Processing Systems. 2016, pp. 1615–1623. Kriege, N. M. et al. “A Unifying View of Explicit and Implicit Feature Maps for Structured Data: Systematic Studies of Graph Kernels”. In: CoRR abs/1703.00676 (2017). url: http://arxiv.org/abs/1703.00676. Kriege, N. et al. “Explicit versus Implicit Graph Feature Maps: A Computational Phase Transition for Walk Kernels”. In: IEEE International Conference on Data Mining. 2014, pp. 881–886. Morris, C., K. Kersting, and M. Mutzel. “Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs”. In: IEEE International Conference on Data Mining. 2017. 19
  • 38. References II Morris, C. et al. “Faster Kernel for Graphs with Continuous Attributes via Hashing”. In: IEEE International Conference on Data Mining. 2016, pp. 1095–1100. 20