ABSTRACT
Various methods to deal with graph data have been proposed in recent years. However, most of these methods focus on graph feature aggregation rather than graph pooling. Besides, the existing top-k selection graph pooling methods have a few problems. First, to construct the pooled graph topology, current top-k selection methods evaluate the importance of the node from a single perspective only, which is simplistic and unobjective. Second, the feature information of unselected nodes is directly lost during the pooling process, which inevitably leads to a massive loss of graph feature information. To solve these problems mentioned above, we propose a novel graph self-adaptive pooling method with the following objectives: (1) to construct a reasonable pooled graph topology, structure and feature information of the graph are considered simultaneously, which provide additional veracity and objectivity in node selection; and (2) to make the pooled nodes contain sufficiently effective graph information, node feature information is aggregated before discarding the unimportant nodes; thus, the selected nodes contain information from neighbor nodes, which can enhance the use of features of the unselected nodes. Experimental results on four different datasets demonstrate that our method is effective in graph classification and outperforms state-of-the-art graph pooling methods.
- Karpathy A., Toderici G., S. Shetty, T. Leung, Sukthankar R., and Fei-Fei L. 2014. Large-scale video classification with convolutional neural networks.In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2014), 1725–1732.Google Scholar
- Krizhevsky A, Sutskever I, and Hinton G. E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (2012), 1097–1105.Google ScholarDigital Library
- Paszke A., Gross S., Chintala S., Chanan G., Yang E., DeVito Z., Lin, Z., Desmaison A., Antiga L., and Lerer A.2017. Automatic differentiation in pytorch.In NIPS-W (2017).Google Scholar
- Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral Networks and Locally Connected Networks on Graph. Computer Vision and Pattern Recognition(2014).Google Scholar
- Dobson P. D and Doig A. J. 2013. Distinguishing enzyme structures from non-enzymes without alignments. Journal of molecular biology(2013), 771–783.Google Scholar
- Lazer D, Pentland A. S, Adamic L, Aral S, Barabasi A. L, Brewer D, Christakis N, Contractor N, Fowler J, and Gutmann M. 2009. Life in the network: the coming age of computational social science. Science (2009), 721–723. https://doi.org/323(5915):721Google Scholar
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In neural information processing systems(2016).Google Scholar
- Hinton G, Deng L., Yu D., Dahl G. E., A. Mohamed, Jaitly N., and Seniort. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups.IEEE Signal processing magazine(2012), 82–97.Google Scholar
- Gao H. and Ji S. 2019. Graph u-net. In Proceedings of the 36th International Conference on Machine Learning (2019).Google Scholar
- William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. neural information processing systems(2017).Google Scholar
- J J Hopfield. 1982. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the United States of America 79, 8 (1982). https://doi.org/10.1073/pnas.79.8.2554Google Scholar
- Duvenaud D. K., Maclaurin D., Iparraguirre J, Bombarell R., Hirzel T., Aspuru-Guzik A., , and Adams R. P.2015. Convolutional networks on graphs for learning molecular fingerprints. In neural information processing systems(2015), 2224–2232.Google Scholar
- He K, Zhang X, Ren S, and Sun J. 2016. Deep residual learning for image recognition.In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2016), 770–778.Google Scholar
- Kersting K, Kriege N. M., Morris C., Mutzel P., and Neumann M. 2016. Benchmark data sets for graph kernels. neural information processing systems(2016).Google Scholar
- Jeroen Kazius, Ross McGuire, and Roberta Bursi. 2005. Derivation and Validation of Toxicophores for Mutagenicity Prediction. American Chemical Society(2005), 48(1):312–20. https://doi.org/10.1021/jm040835aGoogle Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (2017).Google Scholar
- N. M. Kriege, P.-L. Giscard, and R. Wilson. 2016. On valid optimal assignment kernels and applications to graph classifcation. In Neural Information Processing Systems(2016), 1623–1631.Google Scholar
- A. Krizhevsky, I. Sutskever, and G. E. Hinton.2012. ImageNet classifcation with deep convolutional neural networks.In Advances in Neural Information Processing Systems (2012), 1097–1105.Google Scholar
- Chen-Yu Lee, Patrick Gallagher, and Zhuowen Tu.2018. Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree.IEEE Transactions on Pattern Analysis and Machine Intelligence (2018). https://doi.org/10.1109/TPAMI.2017.2703082Google Scholar
- Junhyun Lee, Junhyun Lee, and Jaewoo Kang. 2019. Self-Attention Graph Pooling. International Conference on Machine Learning (2019).Google Scholar
- Fey M. and Lenssen J. E.2019. Fast Graph Representation Learning with PyTorch Geometric.In ICLR Workshop on Representation Learning on Graphs and Manifolds (2019).Google Scholar
- Yao Ma, Suhang Wang, Charu C. Aggarwal, Xiang Ren, and Jiliang Tang. 2019. Graph Convolutional Networks with EigenPooling. Knowledge Discovery in Database(2019).Google Scholar
- Shervashidze N, Schweitzer P, Leeuwen E. J. v., Mehlhorn K., and Borgwardt K. M. 2011. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research(2011), 1193–1216.Google Scholar
- Wale N., Watson I. A., and Karypis G. 2008. Comparison of descriptor spaces for chemical compound retrieval and classification.Knowledge and Information Systems(2008), 347–375.Google Scholar
- Vinyals O, Bengio S, and Kudlur M. 2015. Order matters: Sequence to sequence for sets. International Conference on Learning Representations (2015).Google Scholar
- Kaspar Riesen and Horst Bunke. 2008. IAM Graph Database Repository for Graph Based Pattern Recognition and Machine Learning. Structural, Syntactic, and Statistical Pattern Recognition (2008), 287–297.Google Scholar
- Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-sne. Journal of Machine Learning Research (9(Nov) 2008), 2579–2605.Google Scholar
- Petar Velickovic, Guillem Cucurul, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph Attention Networks. International Conference on Learning Representations (2018).Google Scholar
- Sijie Yan, Yuanjun Xiong, and Dahua Lin. 2018. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. In the Association for the Advance of Artificial Intelligence (2018).Google Scholar
- Liang Yao, Chengsheng Mao, and Yuan Luo. 2019. Graph Convolutional Networks for Text Classification. the Association for the Advance of Artificial Intelligence (2019).Google Scholar
- Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, and Jure Leskovec. 2018. Hierarchical Graph Representation Learning with Differentiable Pooling. neural information processing systems(2018).Google Scholar
Index Terms
- Structure-Feature based Graph Self-adaptive Pooling
Recommendations
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, ...
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 ...
Masked Graph Auto-Encoder Constrained Graph Pooling
Machine Learning and Knowledge Discovery in DatabasesAbstractThe node drop pooling is a significant type of graph pooling that is required for learning graph-level representations. However, existing node drop pooling models still suffer from the information loss problem, impairing their effectiveness in ...
Comments