{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T03:23:37Z","timestamp":1769743417059,"version":"3.49.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"abstract":"<jats:p>Graph Neural Networks (GNNs) are powerful for the representation learning of graph-structured data. Most of the GNNs use a message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information from its neighbors. To achieve a better expressive capability of node influences, attention mechanism has grown to be popular to assign trainable weights to the nodes in aggregation. Though the attention-based GNNs have achieved remarkable results in various tasks, a clear understanding of their discriminative capacities is missing. In this work, we present a theoretical analysis of the representational properties of the GNN that adopts the attention mechanism as an aggregator. Our analysis determines all cases when those attention-based GNNs can always fail to distinguish certain distinct structures. Those cases appear due to the ignorance of cardinality information in attention-based aggregation. To improve the performance of attention-based GNNs, we propose cardinality preserved attention (CPA) models that can be applied to any kind of attention mechanisms. Our experiments on node and graph classification confirm our theoretical analysis and show the competitive performance of our CPA models. The code is available online: https:\/\/github.com\/zetayue\/CPA.<\/jats:p>","DOI":"10.24963\/ijcai.2020\/194","type":"proceedings-article","created":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T08:12:10Z","timestamp":1594195930000},"page":"1395-1402","source":"Crossref","is-referenced-by-count":46,"title":["Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation"],"prefix":"10.24963","author":[{"given":"Shuo","family":"Zhang","sequence":"first","affiliation":[{"name":"The Graduate Center, The City University of New York"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Ph.D. Program in Computer Science, The Graduate Center, The City University of New York"},{"name":"Department of Computer Science, Hunter College, The City University of New York"},{"name":"Helen & Robert Appel Alzheimer\u2019s Disease Research Institute, Feil Family Brain & Mind Research"},{"name":"Institute, Weill Cornell Medicine, Cornell University"}]}],"member":"10584","event":{"name":"Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}","theme":"Artificial Intelligence","location":"Yokohama, Japan","acronym":"IJCAI-PRICAI-2020","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2020,7,11]]},"end":{"date-parts":[[2020,7,17]]}},"container-title":["Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T22:13:49Z","timestamp":1594246429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2020\/194"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2020\/194","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}