![Experimental Results
PRO IMDB-M NCI1 PTC-FM MUTAG
0
20
40
60
80
100
Accuracy[%]
1-GNN
1-k-GNN
Figure 3: Classification: Improvement on smaller benchmark datasets
14](https://image.slidesharecdn.com/main-181113185224/85/Weisfeiler-and-Leman-Go-Neural-Higher-order-Graph-Neural-Networks-36-320.jpg)
Ad
More Related Content
What's hot (20)
Similar to Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks (20)
Ad
Recently uploaded (20)
![Adamson, Walter L. - Avant-Garde Florence. From Modernism to Fascism [ocr] [...](https://cdn.slidesharecdn.com/ss_thumbnails/adamsonwalterl-250506185430-7d64f4bb-thumbnail.jpg?width=560&fit=bounds)
Ad
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
- 1. Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, Martin Grohe November 12, 2018 TU Dortmund University, RWTH Aachen University, McGill University
- 2. Motivation Question How similar are two graphs? (a) Sildenafil (b) Vardenafil 1
- 3. High-level View: Supervised Graph Classification 2
- 4. High-level View: Supervised Graph Classification ⊆ H φ: G → H 2
- 5. High-level View: Supervised Graph Classification ⊆ H φ: G → H 2
- 6. Talk Structure 1 State-of-the-art methods for graph classification 2 Relationship between 1-WL kernel and Graph Neural Networks 3 Higher-order graph properties 4 Experimental results 3
- 7. Supervised Graph Classification: The State-of-the-Art Kernel Methods Find predefined substructures and count them somehow: • Shortest-paths or random walks • Motifs • h-neighborhoods around vertices • Spectral Approaches 4
- 8. Supervised Graph Classification: The State-of-the-Art Kernel Methods Find predefined substructures and count them somehow: • Shortest-paths or random walks • Motifs • h-neighborhoods around vertices • Spectral Approaches Neural Methods Parameterized neighborhood aggregation function f (t) v = 𝜎(W1 f (t−1) v + W2 ∑︁ w∈N(v) f (t−1) w ) and learn parameters W1 and W2 together with the parameters of the classifier 4
- 9. Example: Weisfeiler-Lehman Subtree Kernel Example (Weisfeiler-Lehman Subtree Kernel) Graph kernel based on heuristic for graph isomorphism testing Iteration: Two vertices get identical colors iff their colored neighborhoods are identical N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt. “Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561 5
- 10. Example: Weisfeiler-Lehman Subtree Kernel Example (Weisfeiler-Lehman Subtree Kernel) Graph kernel based on heuristic for graph isomorphism testing Iteration: Two vertices get identical colors iff their colored neighborhoods are identical 𝜑(G1) = ( ) (a) G1 𝜑(G2) = ( ) (b) G2 N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt. “Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561 5
- 11. Example: Weisfeiler-Lehman Subtree Kernel Example (Weisfeiler-Lehman Subtree Kernel) Graph kernel based on heuristic for graph isomorphism testing Iteration: Two vertices get identical colors iff their colored neighborhoods are identical 𝜑(G1) = (2, 2, 2, ) (a) G1 𝜑(G2) = (1, 1, 3, ) (b) G2 N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt. “Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561 5
- 12. Example: Weisfeiler-Lehman Subtree Kernel Example (Weisfeiler-Lehman Subtree Kernel) Graph kernel based on heuristic for graph isomorphism testing Iteration: Two vertices get identical colors iff their colored neighborhoods are identical 𝜑(G1) = (2, 2, 2, 2, 2, 2, 0, 0) (a) G1 𝜑(G2) = (1, 1, 3, 2, 0, 1, 1, 1) (b) G2 N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt. “Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561 5
- 13. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ 6
- 14. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ 6
- 15. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ Both methods aggregate colors/features of neighbors 6
- 16. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ Both methods aggregate colors/features of neighbors Theorem (Informal) GNNs cannot be more expressive than 1-WL in terms of distinguishing non-isomorphic graphs. 6
- 17. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ 7
- 18. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ Insight GNNs are as powerful as 1-WL if f W (t) 1 merge and f W (t) 2 aggr are injective Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 7
- 19. Relationship between 1-WL and GNN Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 8
- 20. Relationship between 1-WL and GNN Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 1-WL GNN ∇ 8
- 21. Relationship between 1-WL and GNN Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 1-WL GNN ∇ Take Away GNNs have the same power as 1-WL in distinguishing non-isomorphic graphs. 8
- 22. Relationship between 1-WL and GNN Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 1-WL GNN ∇ Take Away GNNs have the same power as 1-WL in distinguishing non-isomorphic graphs. Limits of 1-WL are well understood. V. Arvind, J. Köbler, G. Rattan, and O. Verbitsky. “On the Power of Color Refinement”. In: Symposium on Fundamentals of Computation Theory. 2015, pp. 339–350 8
- 23. Limits of GNNs Observation GNNs cannot distinguish very basic graph properties, e.g., • Cycle-free vs. cyclic graphs • Triangle counts • Regular graphs 9
- 24. Limits of GNNs Observation GNNs cannot distinguish very basic graph properties, e.g., • Cycle-free vs. cyclic graphs • Triangle counts • Regular graphs Observation Higher-order graph properties play an important role for the characterization of real-world networks. 9
- 25. Higher-order Graph Properties Challenge Incorporate more higher-order graph properties into Graph Neural Networks. 10
- 26. Higher-order Graph Properties Challenge Incorporate more higher-order graph properties into Graph Neural Networks. 1-WL GNN k-WL k-GNN ∇ Global Global ∇ 10
- 27. Higher-order Graph Properties Challenge Incorporate more higher-order graph properties into Graph Neural Networks. 1-WL GNN k-WL k-GNN ∇ Global Global ∇ Idea: k-WL Color subgraphs instead of vertices, and define neighborhoods between them. 10
- 28. k-dimensional Weisfeiler-Lehman k-dimensional Weisfeiler-Lehman • Colors vertex tuples from Vk • Two tuples v, w are i-neighbors if vj = wj for all j ̸= i v1 v2 v3 v4 v5 v6 11
- 29. k-dimensional Weisfeiler-Lehman k-dimensional Weisfeiler-Lehman • Colors vertex tuples from Vk • Two tuples v, w are i-neighbors if vj = wj for all j ̸= i v1 v2 v3 v4 v5 v6 11
- 30. k-dimensional Weisfeiler-Lehman k-dimensional Weisfeiler-Lehman • Colors vertex tuples from Vk • Two tuples v, w are i-neighbors if vj = wj for all j ̸= i v1 v2 v3 v4 v5 v6 Idea of the Algorithm Initially Two tuples get the same color if the induced subgraphs are isomorphic 11
- 31. k-dimensional Weisfeiler-Lehman k-dimensional Weisfeiler-Lehman • Colors vertex tuples from Vk • Two tuples v, w are i-neighbors if vj = wj for all j ̸= i v1 v2 v3 v4 v5 v6 Idea of the Algorithm Initially Two tuples get the same color if the induced subgraphs are isomorphic Iteration Two tuples get same color iff they have the same colored neighborhood 11
- 32. k-GNN Idea Derive k-dimensional Graph Neural Network ft S = 𝜎(W1ft−1 S + W2 ∑︁ T∈N(S) ft−1 T ), where S is a subgraph of the input graph of size k. 12
- 33. k-GNN Idea Derive k-dimensional Graph Neural Network ft S = 𝜎(W1ft−1 S + W2 ∑︁ T∈N(S) ft−1 T ), where S is a subgraph of the input graph of size k. Challenges • Scalability • GPU memory consumption 12
- 34. Hierarchical k-GNN Idea Learn features for subgraphs in a hierarchical way 13
- 35. Hierarchical k-GNN Idea Learn features for subgraphs in a hierarchical way 1-GNN . . . 2-GNN . . . 3-GNN . . . MLP Pool Pool Pool Learning higher-order graph properties 13
- 36. Experimental Results PRO IMDB-M NCI1 PTC-FM MUTAG 0 20 40 60 80 100 Accuracy[%] 1-GNN 1-k-GNN Figure 3: Classification: Improvement on smaller benchmark datasets 14
- 37. Experimental Results U0 ZPVE H 0.00 0.25 0.50 0.75 1.00 1.25 1.50 1.75 2.00 Errornormalizedto1-GNN(lowerisbetter) 1-k-GNN 1-GNN MPNN DTNN Figure 4: Regression (QM9 data set): Gain over 1-GNN baseline 15
- 38. Conclusion 1 Relationship between 1-WL kernel and Graph Neural Networks • GNN are a differentiable version of 1-WL • GNNs and 1-WL are equally powerful 2 Higher-order graph embeddings • k-dimensional GNN • Hierarchical Variant 3 Experimental results • Good results for large datasets with continuous node labels 16
- 39. Conclusion 1 Relationship between 1-WL kernel and Graph Neural Networks • GNN are a differentiable version of 1-WL • GNNs and 1-WL are equally powerful 2 Higher-order graph embeddings • k-dimensional GNN • Hierarchical Variant 3 Experimental results • Good results for large datasets with continuous node labels Collection of graph classification benchmarks graphkernels.cs.tu-dortmund.de 16