Abstract
Graph pooling refers to the operation that maps a set of node representations into a compact form for graph-level representation learning. However, existing graph pooling methods are limited by the power of the Weisfeiler–Lehman (WL) test in the performance of graph discrimination. In addition, these methods often suffer from hard adaptability to hyper-parameters and training instability. To address these issues, we propose Hi-PART, a simple yet effective graph neural network (GNN) framework with
- [1] . 2009. Entropy measures for networks: Toward an information theory of complex topologies. Physical Review E 80, 4 (2009), 045102.Google ScholarCross Ref
- [2] . 2016. Graph isomorphism in quasipolynomial time. In Proceedings of the 48th Annual ACM Symposium on Theory of Computing. 684–697.Google Scholar
- [3] J. Baek, M. Kang, and S. J. Hwang. 2021. Accurate learning of graph representations with graph multiset pooling. The International Conference on Learning Representations (ICLR’21).Google Scholar
- [4] . 2020. Spectral clustering with graph neural networks for graph pooling. In Proceedings of the International Conference on Machine Learning. PMLR, 874–883.Google Scholar
- [5] . 2008. Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment 2008, 10 (2008), P10008.Google ScholarCross Ref
- [6] . 2006. The Laplacian of a graph as a density matrix: A basic combinatorial approach to separability of mixed states. Annals of Combinatorics 10, 3 (2006), 291–317.Google ScholarCross Ref
- [7] . 1992. An optimal lower bound on the number of variables for graph identification. Combinatorica 12, 4 (1992), 389–410.Google ScholarCross Ref
- [8] F. Diehl. 2019. Edge contraction pooling for graph neural networks. arXiv preprint arXiv:1905.10990.Google Scholar
- [9] . 2003. Distinguishing enzyme structures from non-enzymes without alignments. Journal of Molecular Biology 330, 4 (2003), 771–783.Google ScholarCross Ref
- [10] . 2007. Random-walk computation of similarities between nodes of a graph with application to collaborative recommendation. IEEE Transactions on Knowledge and Data Engineering 19, 3 (2007), 355–369.Google ScholarDigital Library
- [11] . 2019. Graph U-Nets. In Proceedings of the International Conference on Machine Learning. PMLR, 2083–2092.Google Scholar
- [12] . 2017. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 1025–1035.Google ScholarDigital Library
- [13] T. N. Kipf and M. Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.Google Scholar
- [14] . 2019. Self-attention graph pooling. In Proceedings of the International Conference on Machine Learning. PMLR, 3734–3743.Google Scholar
- [15] . 2016. Structural information and dynamical complexity of networks. IEEE Transactions on Information Theory 62, 6 (2016), 3290–3339.Google ScholarDigital Library
- [16] . 2020. Towards deeper graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 338–348.Google ScholarDigital Library
- [17] . 2019. Graph convolutional networks with eigenpooling. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 723–731.Google ScholarDigital Library
- [18] C. Morris, M. N. Kriege, F. Bause, et al. 2020. Tudataset: A collection of benchmark datasets for learning with graphs. arXiv preprint arXiv:2007.08663.Google Scholar
- [19] . 2004. Fast algorithm for detecting community structure in networks. Physical Review E 69, 6 (2004), 066133.Google ScholarCross Ref
- [20] . 2004. Finding and evaluating community structure in networks. Physical Review E 69, 2 (2004), 026113.Google ScholarCross Ref
- [21] . 2021. Graph pooling via coarsened graph infomax. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2177–2181.Google ScholarDigital Library
- [22] . 2020. ASAP: Adaptive structure aware pooling for learning hierarchical graph representations. In Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34, 5470–5477.Google ScholarCross Ref
- [23] . 1955. Life, information theory, and topology. The Bulletin of Mathematical Biophysics 17, 3 (1955), 229–235.Google ScholarCross Ref
- [24] . 1948. A mathematical theory of communication. The Bell System Technical Journal 27, 3 (1948), 379–423.Google ScholarCross Ref
- [25] . 2021. Hierarchical graph representation learning with local capsule pooling. In ACM Multimedia Asia. 1–7.Google Scholar
- [26] P. Veličković, G. Cucurull, A. Casanova, et al. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903.Google Scholar
- [27] . 2008. Comparison of descriptor spaces for chemical compound retrieval and classification. Knowledge and Information Systems 14, 3 (2008), 347–375.Google ScholarDigital Library
- [28] . 2020. Haar graph pooling. In Proceedings of the International Conference on Machine Learning. PMLR, 9952–9962.Google Scholar
- [29] Z. Wang and S. Ji. 2020. Second-order pooling for graph neural networks. IEEE Transactions on Pattern Analysis & Machine Intelligence 1 (2020), 1–1.Google Scholar
- [30] . 1968. The reduction of a graph to canonical form and the algebra which appears therein. NTI, Series 2, 9 (1968), 12–16.Google Scholar
- [31] K. Xu, W. Hu, J. Leskovec, et al. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826.Google Scholar
- [32] . 2015. Deep graph kernels. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1365–1374.Google ScholarDigital Library
- [33] . 2015. A structural smoothing framework for robust graph comparison. In Proceedings of the 28th International Conference on Neural Information Processing Systems . 2134–2142.Google Scholar
- [34] Z. Ying, J. You, C. Morris, et al. 2018. Hierarchical graph representation learning with differentiable pooling. Advances in Neural Information Processing Systems. (2018), 31.Google Scholar
- [35] . 2021. Identity-aware graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 35, 10737–10745.Google ScholarCross Ref
- [36] . 2020. StructPool: Structured graph pooling via conditional random fields. In Proceedings of the 8th International Conference on Learning Representations.Google Scholar
- [37] . 2018. Link prediction based on graph neural networks. In Proceedings of the International Conference on Neural Information Processing Systems . 5165–5175.Google Scholar
- [38] . 2018. An end-to-end deep learning architecture for graph classification. In Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 32.Google ScholarCross Ref
- [39] J. Zhou, G. Cui, S. Hu, et al. 2020. Graph neural networks: A review of methods and applications. AI Open, 1 (2020), 57–81.Google Scholar
Index Terms
- Hi-PART: Going Beyond Graph Pooling with Hierarchical Partition Tree for Graph-Level Representation Learning
Recommendations
Graph Representation Learning: Foundations, Methods, Applications and Systems
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningGraphs such as social networks and molecular graphs are ubiquitous data structures in the real world. Due to their prevalence, it is of great research importance to extract meaningful patterns from graph structured data so that downstream tasks can be ...
Multi-scale Graph Pooling Approach with Adaptive Key Subgraph for Graph Representations
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementThe recent progress in graph representation learning boosts the development of many graph classification tasks, such as protein classification and social network classification. One of the mainstream approaches for graph representation learning is the ...
Node Information Awareness Pooling for Graph Representation Learning
Advances in Knowledge Discovery and Data MiningAbstractGraph neural networks (GNNs), which generalize deep neural network models to graph structure data, have attracted increasing attention and achieved state-of-the-art performance in graph-related tasks such as graph classification, link prediction, ...
Comments