Uniform Pooling for Graph Networks
Source abstract
Abstract
The graph convolution network has received a lot of attention because it extends the convolution to non-Euclidean domains. However, the graph pooling method is still less concerned, which can learn coarse graph embedding to facilitate graph classification. Previous pooling methods were based on assigning a score to each node and then pooling only the highest-scoring nodes, which might throw away whole neighbourhoods of nodes and therefore information. Here, we proposed a novel pooling method UGPool with a new point-of-view on selecting nodes. UGPool learns node scores based on node features and uniformly pools neighboring nodes instead of top nodes in the score-space, resulting in a uniformly coarsened graph. In multiple graph classification tasks, including the protein graphs, the biological graphs and the brain connectivity graphs, we demonstrated that UGPool outperforms other graph pooling methods while maintaining high efficiency. Moreover, we also show that UGPool can be integrated with multiple graph convolution networks to effectively improve performance compared to no pooling.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Bioinformatics and Genomic Networks · Complex Network Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
The College of System Engineering, National University of Defense Technology, Changsha 410073, China
The Center for Machine Vision and Signal Analysis, University of Oulu, 90014 Oulu, Finland
Funding
National Natural Science Foundation of China · National Key Research and Development Program · Science and Technology Innovation Program of Hunan Province
References (50)
Show source-provided references
1. Deep learning10.1038/nature14539 ↗
2. A deep CNN approach to decode motor preparation of upper limbs from time–frequency maps of EEG signals at source level10.1016/j.neunet.2020.01.027 ↗
3. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–8). Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Stateline, NV, USA.
4. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
5. Deep Neural Networks for Acoustic Modeling in Speech Recognition10.1109/MSP.2012.2205597 ↗
6. Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., and Li, F.-F. (2014, January 24–27). Large-scale Video Classification with Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.223 ↗
7. Kipf, T.N., and Welling, M. (2017, January 24–26). Semi-supervised classification with graph convolutional networks. Proceedings of the International Conference on Learning Representations, Toulon, France.
8. Defferrard, M., Bresson, X., and Vandergheynst, P. (2016, January 5–10). Convolutional neural networks on graphs with fast localized spectral filtering. Proceedings of the Advances in Neural Information Processing Systems, Barcelona, Spain.
9. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (May, January 30). Graph attention networks. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
10. Fout, A., Byrd, J., Shariat, B., and Ben-Hur, A. (2017, January 4–9). Protein interface prediction using graph convolutional networks. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
11. Li, B., Li, X., Zhang, Z., and Wu, F. (February, January 27). Spatio-temporal graph routing for skeleton-based action recognition. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
12. Guo, K., Hu, Y., Qian, Z., Liu, H., Zhang, K., Sun, Y., Gao, J., and Yin, B. (2020). Optimized Graph Convolution Recurrent Neural Network for Traffic Prediction. IEEE Trans. Intell. Transp. Syst., 1–12.
13. Berg, R.v.d., Kipf, T.N., and Welling, M. (2017). Graph convolutional matrix completion. arXiv.
14. Yao, L., Mao, C., and Luo, Y. (February, January 27). Graph convolutional networks for text classification. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
15. You, J., Liu, B., Ying, Z., Pande, V., and Leskovec, J. (2018, January 2–8). Graph convolutional policy network for goal-directed molecular graph generation. Proceedings of the Advances in Neural Information Processing Systems, Montréal, QC, Canada.
16. Modeling polypharmacy side effects with graph convolutional networks10.1093/bioinformatics/bty294 ↗
17. Peng, H., Li, J., He, Y., Liu, Y., Bao, M., Wang, L., Song, Y., and Yang, Q. (2018, January 23–27). Large-scale hierarchical text classification with recursively regularized deep graph-cnn. Proceedings of the 2018 World Wide Web Conference. International World Wide Web Conferences Steering Committee, Lyon, France.10.1145/3178876.3186005 ↗
18. Rhee, S., Seo, S., and Kim, S. (2018, January 13–19). Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification. Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/490 ↗
19. Ma, Y., Wang, S., Aggarwal, C.C., and Tang, J. (2019). Graph Convolutional Networks with EigenPooling. arXiv.10.1145/3292500.3330982 ↗
20. Ying, Z., You, J., Morris, C., Ren, X., Hamilton, W., and Leskovec, J. (2018, January 2–8). Hierarchical graph representation learning with differentiable pooling. Proceedings of the Advances in Neural Information Processing Systems, Montréal, QC, Canada.
21. Gao, H., and Ji, S. (2019, January 10–15). Graph U-Nets. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
22. Cangea, C., Veličković, P., Jovanović, N., Kipf, T., and Liò, P. (2018, January 8). Towards sparse hierarchical graph classifiers. Proceedings of the NeurIPS Workshop on Relational Representation Learning, Montréal, QC, Canada.
23. Lee, J., Lee, I., and Kang, J. (2019, January 10–15). Self-Attention Graph Pooling. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
24. Diehl, F., Brunner, T., Michael, T.L., and Knoll, A. (2019, January 15). Towards Graph Pooling by Edge Contraction. Proceedings of the ICML Workshop on Learning and Reasoning with Graph-Structured Data, Los Angeles, CA, USA.
25. Xu, K., Hu, W., Leskovec, J., and Jegelka, S. (2019, January 6–9). How powerful are graph neural networks?. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA.
26. Bruna, J., Zaremba, W., Szlam, A., and LeCun, Y. (2014, January 14–16). Spectral networks and locally connected networks on graphs. Proceedings of the International Conference on Learning Representations, Banff, AB, Canada.
27. Henaff, M., Bruna, J., and LeCun, Y. (2015). Deep convolutional networks on graph-structured data. arXiv.
28. Hamilton, W., Ying, Z., and Leskovec, J. (2017, January 4–9). Inductive representation learning on large graphs. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
29. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT press.
30. Weighted graph cuts without eigenvectors a multilevel approach10.1109/TPAMI.2007.1115 ↗
31. Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., and Dahl, G.E. (2017, January 6–22). Neural message passing for quantum chemistry. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia.
32. Vinyals, O., Bengio, S., and Kudlur, M. (2015, January 7–9). Order matters: Sequence to sequence for sets. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA.
33. Zhang, M., Cui, Z., Neumann, M., and Chen, Y. (2018, January 2–7). An end-to-end deep learning architecture for graph classification. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11782 ↗
34. Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., and Weinberger, K. (2019, January 10–15). Simplifying Graph Convolutional Networks. Proceedings of the 36th International Conference on Machine Learning, PMLR, Long Beach, CA, USA.
35. Shchur, O., Mumme, M., Bojchevski, A., and Günnemann, S. (2018). Pitfalls of graph neural network evaluation. arXiv.
36. Kersting, K., Kriege, N.M., Morris, C., Mutzel, P., and Neumann, M. (2016, April 08). Benchmark Data Sets for Graph Kernels. Available online: http://graphkernels.cs.tu-dortmund.de.
37. Distinguishing enzyme structures from non-enzymes without alignments10.1016/S0022-2836(03)00628-4 ↗
38. Protein function prediction via graph kernels10.1093/bioinformatics/bti1007 ↗
39. Feragen, A., Kasenburg, N., Petersen, J., de Bruijne, M., and Borgwardt, K. (2013, January 5–10). Scalable kernels for graphs with continuous attributes. Proceedings of the Advances in Neural Information Processing Systems, Stateline, NV, USA.
40. Comparison of descriptor spaces for chemical compound retrieval and classification10.1007/s10115-007-0103-5 ↗
41. The human connectome: A complex network10.1111/j.1749-6632.2010.05888.x ↗
42. Prediction of Individual Brain Maturity Using fMRI10.1126/science.1194144 ↗
43. Identifying major depression using whole-brain functional connectivity: a multivariate pattern analysis10.1093/brain/aws059 ↗
44. Safe Classification With Augmented Features10.1109/TPAMI.2018.2849378 ↗
45. Gender Identification of Human Brain Image with A Novel 3D Descriptor10.1109/TCBB.2015.2448081 ↗
46. Resting-state fMRI in the human connectome project10.1016/j.neuroimage.2013.05.039 ↗
47. The autism brain imaging data exchange: Towards a large-scale evaluation of the intrinsic brain architecture in autism10.1038/mp.2013.78 ↗
48. Discriminative analysis of resting-state functional connectivity patterns of schizophrenia using low dimensional embedding of fMRI10.1016/j.neuroimage.2009.11.011 ↗
49. A whole brain fMRI atlas generated via spatially constrained spectral clustering10.1002/hbm.21333 ↗
50. Metric learning with spectral graph convolutions on brain connectivity networks10.1016/j.neuroimage.2017.12.052 ↗