{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T08:05:31Z","timestamp":1766390731764,"version":"3.48.0"},"reference-count":25,"publisher":"American Association for the Advancement of Science (AAAS)","content-domain":{"domain":["spj.science.org"],"crossmark-restriction":true},"short-container-title":["Intell Comput"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Graph neural networks are powerful for graph-structured data, with graph pooling critical for tasks like classification. Graph pooling methods discard nodes to form a coarser graph representation, while recent expert pooling approaches leverage multiple experts to score and robustly select nodes for retention, capturing diverse graph characteristics, leading to poor performance on complex graphs. To address this, we propose Mutual Information Graph Pooling with Experts, which first assigns each expert to evaluate only a subset of similar nodes, improving scalability and performance on complex graphs, and, second, incorporates frequency-domain representations, ensuring applicability across diverse graph types. We perform pooling based on mutual information across both frequency and spatial domains. Extensive experiments demonstrate that our method outperforms state-of-the-art pooling techniques.<\/jats:p>","DOI":"10.34133\/icomputing.0231","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:10:56Z","timestamp":1762128656000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Mutual Information with Experts: An Approach to Graph Pooling for Graph Neural Networks"],"prefix":"10.34133","volume":"4","author":[{"given":"Tong","family":"Yang","sequence":"first","affiliation":[{"name":"Donghua University","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Li","sequence":"additional","affiliation":[{"name":"Donghua University","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"issue":"7","key":"e_1_3_3_2_2","first-page":"3496","article-title":"Graph neural networks with convolutional ARMA filters","volume":"44","author":"Bianchi FM","year":"2022","unstructured":"Bianchi FM, Grattarola D, Livi L, Alippi C. Graph neural networks with convolutional ARMA filters. IEEE Trans Pattern Anal Mach Intell. 2022;44(7):3496\u20133507.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"e_1_3_3_3_2","unstructured":"Ying Z You J Morris C Ren X Hamilton WL Leskovec J. Hierarchical graph representation learning with differentiable pooling. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montreal (Canada): Curran Associates Inc.; 2018. p. 4805\u20134815."},{"key":"e_1_3_3_4_2","unstructured":"Lee J Lee I Kang J. Self-attention graph pooling. In: Proceedings of the 36th International Conference on Machine Learning. Long Beach (CA): PMLR; 2019. p. 3734\u20133743."},{"issue":"2","key":"e_1_3_3_5_2","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1109\/TCSS.2022.3169219","article-title":"Multistructure graph classification method with attention-based pooling","volume":"10","author":"Xu Y","year":"2022","unstructured":"Xu Y, Wang J, Guang M, Yan C, Jiang C. Multistructure graph classification method with attention-based pooling. IEEE Trans Comput Soc Syst. 2022;10(2):602\u2013613.","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"e_1_3_3_6_2","unstructured":"Kipf TN Welling M. Semi-supervised classification with graph convolutional networks. In: Proceedings of the International Conference on Learning Representations. Toulon (France): OpenReview.net; 2017. p. 1\u201314."},{"key":"e_1_3_3_7_2","unstructured":"Hamilton WL Ying R Leskovec J. Inductive representation learning on large graphs. In: Proceedings of the 31st Conference on Neural Information Processing Systems. Long Beach (CA): Curran Associates Inc.; 2017. p. 1025\u20131035."},{"key":"e_1_3_3_8_2","unstructured":"Velickovic P Cucurull G Casanova A Romero A Lio P Bengio Y. Graph attention networks. In: Proceedings of the International Conference on Learning Representations. Vancouver (Canada): OpenReview.net; 2018. p. 1\u201312."},{"key":"e_1_3_3_9_2","unstructured":"Yuan H Ji S. StructPool: Structured graph pooling via conditional random fields. In: Proceedings of the International Conference on Learning Representations. Addis Ababa (Ethiopia): OpenReview.net; 2020. p. 26\u201330."},{"key":"e_1_3_3_10_2","unstructured":"Li G Muller M Ghanem B Koltun V. Training graph neural networks with 1000 layers. In: Proceedings of the 38 th International Conference on Machine Learning. Virtual Event: PMLR; 2021. Vol. 139 p. 6437\u20136449."},{"issue":"1","key":"e_1_3_3_11_2","first-page":"545","article-title":"Hierarchical multi-view graph pooling with structure learning","volume":"35","author":"Zhang Z","year":"2023","unstructured":"Zhang Z, Bu J, Ester M, Zhang J, Li Z, Yao C, Dai H, Yu Z, Wang C. Hierarchical multi-view graph pooling with structure learning. IEEE Trans Knowl Data Eng. 2023;35(1):545\u2013559.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"e_1_3_3_12_2","unstructured":"Shazeer N Mirhoseini A Maziarz K Davis A Le Q Hinton G Dean J. Outrageously large neural networks: The sparsely gated mixture-of-experts layer. In: Proceedings of the International Conference on Learning Representations. Toulon (France): Open Review.net.; 2017. p. 24\u201326."},{"key":"e_1_3_3_13_2","unstructured":"Wang Y Ma X Zhang G Ni Y Chandra A Guo S Ren W Aruraj A He X Jiang Z et\u00a0al. MMLU-Pro: A more robust and challenging multi-task language understanding benchmark. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver (Canada): PMLR; 2024. Vol. 38."},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2836(03)00628-4"},{"key":"e_1_3_3_15_2","unstructured":"Morris C Kriege NM Bause F Kersting K Mutzel P Neumann M. TUDataset: Collection of benchmark datasets for learning with graphs. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2007.08663"},{"issue":"3","key":"e_1_3_3_16_2","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1007\/s10115-007-0103-5","article-title":"Comparison of descriptor spaces for chemical compound retrieval and classification","volume":"14","author":"Wale N","year":"2008","unstructured":"Wale N, Watson I, Karypis G. Comparison of descriptor spaces for chemical compound retrieval and classification. Knowl Inf Syst. 2008;14(3):347\u2013375.","journal-title":"Knowl Inf Syst"},{"issue":"1","key":"e_1_3_3_17_2","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1021\/jm040835a","article-title":"Derivation and validation of toxicophores for mutagenicity prediction","volume":"48","author":"Kazius J","year":"2005","unstructured":"Kazius J, McGuire R, Bursi R. Derivation and validation of toxicophores for mutagenicity prediction. J Med Chem. 2005;48(1):312\u2013320.","journal-title":"J Med Chem"},{"key":"e_1_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Yanardag P Vishwanathan SVN. Deep graph kernels. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Sydney (Australia): ACM; 2015. p. 1365\u20131374.","DOI":"10.1145\/2783258.2783417"},{"key":"e_1_3_3_19_2","unstructured":"Paszke A Gross S Chintala S Chanan G Yang E Devito Z Lin Z Desmaison A Antiga L Lerer A. Automatic differentiation in Pytorch. In: Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017). Long Beach (CA): OpenReview.net; 2017."},{"key":"e_1_3_3_20_2","unstructured":"Vinyals O Bengio S Kudlur M. Order matters: Sequence to sequence for sets. In: Proceedings of the International Conference on Learning Representations. San Juan (Puerto Rico): ICLR; 2016. p. 1\u201312."},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Zhang M Cui Z Neumann M Chen Y. An end-to-end deep learning architecture for graph classification. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence. New Orleans (LA): AAAI Press; 2018. Vol. 32 p. 4438\u20134445.","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"e_1_3_3_22_2","unstructured":"Baek J Kang M Hwang SJ. Accurate learning of graph representations with graph multiset pooling. In: Proceedings of the International Conference on Learning Representations. Virtual Event: OpenReview.net; 2021. p. 1\u201322."},{"key":"e_1_3_3_23_2","unstructured":"Gao H Ji S. Graph U-Nets. In: Proceedings of the 36th International Conference on Machine Learning. Long Beach (CA): PMLR; 2019. Vol. 97 p. 2083\u20132092."},{"key":"e_1_3_3_24_2","unstructured":"Diehl F. Edge contraction pooling for graph neural networks. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1905.10990"},{"key":"e_1_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Ranjan E Sanyal S Talukdar P. ASAP: Adaptive structure aware pooling for learning hierarchical graph representations. In: Proceedings of the AAAI Conference on Artificial Intelligence. New York (NY): AAAI Press; 2020. Vol. 34. p. 5470\u20135477.","DOI":"10.1609\/aaai.v34i04.5997"},{"key":"e_1_3_3_26_2","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus W","year":"2022","unstructured":"Fedus W, Zoph B, Shazeer N. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. J Mach Learn Res. 2022;23:1\u201339.","journal-title":"J Mach Learn Res"}],"container-title":["Intelligent Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.34133\/icomputing.0231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T08:00:21Z","timestamp":1766390421000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.34133\/icomputing.0231"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":25,"alternative-id":["10.34133\/icomputing.0231"],"URL":"https:\/\/doi.org\/10.34133\/icomputing.0231","relation":{},"ISSN":["2771-5892"],"issn-type":[{"type":"electronic","value":"2771-5892"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-07-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"0231"}}