An Efficient Loop and Clique Coarsening Algorithm for Graph Classification
Abstract: Graph Transformers (GTs) have made remarkable achievements in graph-level tasks. However, most existing works regard graph structures as a form of guidance or bias for enhancing node representations, which focuses on node-central perspectives and lacks explicit representations of edges and structures. One natural question arises as to whether we can leverage a hypernode to represent some structures. Through experimental analysis, we explore the feasibility of this assumption. Based on our findings, we propose an efficient Loop and Clique Coarsening algorithm with linear complexity for Graph Classification (LCC4GC) on GT architecture. Specifically, we build three unique views, original, coarsening, and conversion, to learn a thorough structural representation. We compress loops and cliques via hierarchical heuristic graph coarsening and restrict them with well-designed constraints, which builds the coarsening view to learn high-level interactions between structures. We also introduce line graphs for edge embeddings and switch to edge-central perspective to alleviate the impact of coarsening reduction. Experiments on eight real-world datasets demonstrate the improvements of LCC4GC over 31 baselines from various architectures.
- Accurate learning of graph representations with graph multiset pooling. In ICLR, 2021.
- The maximum clique problem. In Handbook of Combinatorial Optimization. 1999.
- Graph neural networks for link prediction with subgraph sketching. In ICLR, 2023.
- Direct embedding of temporal network edges via time-decayed line graphs. In ICLR, 2023.
- LSGNN: towards general graph neural network in node classification by local similarity. In IJCAI, 2023.
- Graph propagation transformer for graph representation learning. In IJCAI, 2023.
- Exploring network structure, dynamics, and function using networkx. In Proceedings of the 7th Python in Science Conference, 2008.
- Inductive representation learning on large graphs. In NeurIPS, 2017.
- T2-GNN: graph neural networks for graphs with incomplete features and structure via teacher-student distillation. In AAAI, 2023.
- Mpool: Motif-based graph pooling. In PAKDD, 2023.
- Adam: A method for stochastic optimization. In ICLR, 2015.
- Self-attention graph pooling. In ICML, 2019.
- Compact graph structure learning via mutual information compression. In WWW, 2022.
- Gapformer: Graph transformer with graph pooling for node classification. In IJCAI, 2023.
- Multi-scale subgraph contrastive learning. In IJCAI, 2023.
- Self-supervised graph-level representation learning with adversarial contrastive learning. TKDD, 2023.
- Multi-scale graph pooling approach with adaptive key subgraph for graph representations. In CIKM, 2023.
- Multi-view robust graph representation learning for graph classification. In IJCAI, 2023.
- EPT-GCN: edge propagation-based time-aware graph convolution network for POI recommendation. Neurocomputing, 2023.
- Tudataset: A collection of benchmark datasets for learning with graphs. CoRR, abs/2007.08663, 2020.
- Universal graph transformer self-attention networks. In WWW, 2022.
- Learning convolutional neural networks for graphs. In ICML, 2016.
- Uncovering the overlapping community structure of complex networks in nature and society. Nature, 2005.
- Efficient graphlet kernels for large graph comparison. In AISTATS, 2009.
- Weisfeiler-lehman graph kernels. J. Mach. Learn. Res., 2011.
- Exphormer: Sparse transformers for graphs. In ICML, 2023.
- Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In ICLR, 2020.
- R. E Trajan. Depth fisrt search and linear graph algorithms. Siam J Computing, 1974.
- Graph attention networks. In ICLR, 2018.
- Learning hierarchical protein representations via complete 3d graph networks. In ICLR, 2023.
- Pooling architecture search for graph classification. In CIKM, 2021.
- A comprehensive survey on graph neural networks. TNNLS, 2021.
- Structural entropy guided graph hierarchical pooling. In ICML, 2022.
- Nodeformer: A scalable graph structure learning transformer for node classification. In NeurIPS, 2022.
- KDLGT: A linear graph transformer framework via kernel decomposition approach. In IJCAI, 2023.
- Capsule graph neural network. In ICLR, 2019.
- How powerful are graph neural networks? In ICLR, 2019.
- A comprehensive survey of graph-level learning. CoRR, abs/2301.05860, 2023.
- Improving the expressiveness of k-hop message-passing gnns by injecting contextualized substructure information. In KDD, 2023.
- Hierarchical graph representation learning with differentiable pooling. In NeurIPS, 2018.
- Do transformers really perform badly for graph representation? In NeurIPS, 2021.
- MUSE: multi-view contrastive learning for heterophilic graphs via information reconstruction. In CIKM, 2023.
- An end-to-end deep learning architecture for graph classification. In AAAI, 2018.
- RDGSL: dynamic graph representation learning with structure learning. In CIKM, 2023.
- Contrastive cross-scale graph knowledge synergy. In KDD, 2023.
- Hierarchical multi-view graph pooling with structure learning. TKDE, 2023.
- Molhf: A hierarchical normalizing flow for molecular graph generation. In IJCAI, 2023.
- SE-GSL: A general and effective graph structure learning framework through structural entropy optimization. In WWW, 2023.
Paper Prompts
Sign up for free to create and run prompts on this paper.