{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T07:04:44Z","timestamp":1780383884272,"version":"3.54.1"},"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) have been shown to be  powerful in a wide range of graph-related tasks. While there exists various GNN models, a critical common ingredient is neighborhood aggregation, where the embedding of each node is updated by referring to the embedding of its neighbors. This paper aims to provide a better understanding of this mechanisms by asking the following question: Is neighborhood aggregation always necessary and beneficial? In short, the answer is no. We carve out two conditions under which neighborhood aggregation is not helpful: (1) when a node's neighbors are highly dissimilar and (2) when a node's embedding is already similar with that of its neighbors. We propose novel metrics that quantitatively measure these two circumstances and integrate them into an Adaptive-layer module. Our experiments show that allowing for node-specific aggregation degrees have significant advantage over current GNNs.<\/jats:p>","DOI":"10.24963\/ijcai.2020\/181","type":"proceedings-article","created":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T12:12:10Z","timestamp":1594210330000},"page":"1303-1309","source":"Crossref","is-referenced-by-count":49,"title":["When Do GNNs Work: Understanding and Improving Neighborhood Aggregation"],"prefix":"10.24963","author":[{"given":"Yiqing","family":"Xie","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology"},{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sha","family":"Li","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carl","family":"Yang","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raymond Chi-Wing","family":"Wong","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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":[[2020,7,9]],"date-time":"2020-07-09T02:13:45Z","timestamp":1594260825000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2020\/181"}},"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\/181","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}