KYHTQT.

A generalized Aggregation Method for Message Passing Graph Neural Networks

Năm XB 2024 Tạp chí / Hội thảo Lecture Notes in Networks and Systems Volume 1205 LNNS Đơn vị CNTT DOI / Link https://doi.org/10.1007/978-3-031-80943-9_46 ↗

Tác giả

Trung-Nghia Phung

Tóm tắt

Graph Neural Networks (GNNs) have emerged as one of the most powerful tools for graph structure modeling. They have been successfully applied to solve different tasks in various domains and have gained impressive performances. Most GNNs are based on Message-Passing Neural Networks (MPNN), in which the representation update of a node is done iteratively. In each iteration, the update of a node representation only involves the information from its neighbors, leaving distant nodes untouched. Hence, it might not capture sufficient information. Here, we assume that the combination of information from neighboring and distant nodes whose high similarities with the current node measured by graph node kernels can improve the performance of the MPNN-based models. Therefore, we propose a generalized aggregation method that improves the performances of existing MPNN-based models. The evaluation results from various settings using different datasets and MPNN-based models confirm the potential of our proposed method.

Tài liệu tham khảo

[1] Zheng, W., et al.: A graph kernel based on context vectors for extracting drug-drug interactions. J. Biomed. Inform. 61, 34–43 (2016)

[2] Zampieri, G., et al.: Scuba: scalable kernel-based gene prioritization. BMC Bioinform. 19, 1–12 (2018)

[3] Mautner, S., Montaseri, S., Miladi, M., Raden, M., Costa, F., Backofen, R.: Shaker: RNA shape prediction using graph kernel. Bioinformatics 35(14), 354–359 (2019)

[4] Tran, V.D., Sperduti, A., Backofen, R., Costa, F.: Heterogeneous networks integration for disease-gene prioritization with node kernels. Bioinformatics 36(9), 2649–2656 (2020)

[5] Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI Open 1, 57–81 (2020)

[6] Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: International Conference on Machine Learning, pp. 1263–1272. PMLR (2017)

[7] Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)

[8] Velickovic, P., et al.: Graph attention networks. Stat 1050(20), 10–48550 (2017)

[9] Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018)

[10] Tran, D.V., Navarin, N., Sperduti, A.: On filter size in graph convolutional networks. In: 2018 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1534–1541. IEEE (2018)

[11] Kondor, R.I., Lafferty, J.: Diffusion kernels on graphs and other discrete structures. In: Proceedings of the 19th International Conference on Machine Learning, vol. 2002, pp. 315–322 (2002)

[12] Chebotarev, P., Shamis, E.: The matrix-forest theorem and measuring relations in small social groups. arXiv preprint math/0602070 (2006)

[13] Chen, B., Li, M., Wang, J., Wu, F.-X.: Disease gene identification by using graph kernels and markov random fields. Sci. China Life Sci. 57, 1054–1063 (2014)

[14] Haussler, D., et al.: Convolution kernels on discrete structures. Technical report, Citeseer (1999)

[15] Shervashidze, N., Schweitzer, P., Van Leeuwen, E.J., Mehlhorn, K., Borgwardt, K.M.: Weisfeiler-Lehman graph kernels. J. Mach. Learn. Res. 12(9) (2011)

[16] Costa, F., Grave, K.D.: Fast neighborhood subgraph pairwise distance kernel. In: Proceedings of the 27th International Conference on International Conference on Machine Learning, pp. 255–262 (2010)

[17] Debnath, A.K., Compadre, R.L., Debnath, G., Shusterman, A.J., Hansch, C.: Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. J. Med. Chem. 34(2), 786–797 (1991)

[18] Kriege, N., Mutzel, P.: Subgraph matching kernels for attributed graphs. arXiv preprint arXiv:1206.6483 (2012)

[19] Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. Adv. Neural Inf. Process. Syst. 30 (2017)

[20] Wale, N., Watson, I.A., Karypis, G.: Comparison of descriptor spaces for chemical compound retrieval and classification. Knowl. Inf. Syst. 14, 347–375 (2008)

[21] Sutherland, J.J., O’brien, L.A., Weaver, D.F.: Spline-fitting with a genetic algorithm: a method for developing classification structure- activity relationships. J. Chem. Inf. Comput. Sci. 43(6), 1906–1915 (2003)

[22] Borgwardt, K.M., Ong, C.S., Schönauer, S., Vishwanathan, S., Smola, A.J., Kriegel, H.-P.: Protein function prediction via graph kernels. Bioinformatics 21(suppl 1), 47–56 (2005)

[23] Dobson, P.D., Doig, A.J.: Distinguishing enzyme structures from non-enzymes without alignments. J. Mol. Biol. 330(4), 771–783 (2003)

[24] Paszke, A., et al.: PyTorch: an imperative style, high performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)

[25] Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch geometric. arXiv preprint arXiv:1903.02428 (2019)

[26] Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)

[27] Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)

Ghi chú

ICTA

← Quay lại danh sách bài báo