A curated list of awesome high expressive GNNs for graph classification. (Actively keep updating)
- Survey Papers
- Weisfeiler-Leman
- High-order WL-based Methods
- Augmented feature-based Methods
- Subgraph-based Methods
- k-hop Message Passing GNNs
- Equivariant Graph Networks
- A Survey on The Expressive Power of Graph Neural Networks Ryoma Sato. 2020.
- The Expressive Power of Graph Neural Networks Pan Li et al. 2022.
- A Theoretical Comparison of Graph Neural Network Extensions Pal Andras Papp et al. 2022.
-
The reduction of a graph to canonical form and the algebra which appears therein Boris Weisfeiler and Andrey Lehman 1968.
-
Weisfeiler-Lehman Graph Kernels Nino Shervashidze. 2011.
-
Power and Limits of the Weisfeiler-Leman Algorithm Sandra Kiefer. 2020.
-
The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs Christopher Morris et al. 2021.
-
Weisfeiler and Leman go Machine Learning: The Story so far Christopher Morris et al. 2021.
-
A Short Tutorial on The Weisfeiler-Lehman Test And Its Variants Ningyuan Huang et al. 2022.
-
How Powerful are Graph Neural Networks? Keyulu Xu et al. ICLR 2019.[code]
- Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks Christopher Morris et al. AAAI 2019. [code] (k-GNN)
- Provably Powerful Graph Networks Haggai Maron et al. NeurIPS 2019. [code] (PPGN)
- What graph neural networks cannot learn: depth vs width Andreas Loukas ICLR 2020.
- Random Features Strengthen Graph Neural Networks Ryoma Sato et al. SIAM 2021. [code]
- The Surprising Power of Graph Neural Networks with Random Node Initialization Ralph Abboud et al. IJCAI 2021. [code]
- Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning Pan Li et al. NeurIPS 2020. [code] (DE-GNN)
- Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks Haorui Wang et al. ICLR 2022. [code] (PEG)
- Nested Graph Neural Networks Muhan Zhang et al. NeurIPS 2021. [code] (NGNN)
- Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks Dylan Sandfelder et al. ICASSP 2021. (Ego-GNN)
- From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness Lingxiao Zhao et al. ICLR 2022. [code] (GNN-AK)
- Equivariant Subgraph Aggregation Networks Beatrice Bevilacqua et al. ICLR 2022. [code] (ESAN)
- Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries Fabrizio Frasca et al. 2022
- Ordered Subgraph Aggregation Networks Chendi Qian et al. 2022
- MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing Sami Abu-El-Haija. et al. ICML 2019. [code] (MixHop)
- k-hop graph neural networks Giannis Nikolentzos et.al. Neural Networks 2020.[code] (k-hop GNN)
- Multi-hop Attention Graph Neural Networks Guangtao Wang et al. IJCAI 2021.
- Shortest Path Networks for Graph Property Prediction Ralph Abboud et al. 2022.
- How Powerful are K-hop Message Passing Graph Neural Networks Jiarui Feng et al. 2022. [code]
- Invariant and Equivariant Graph Networks Haggai Maron et al. ICLR 2019.