{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/geniepath-graph-neural-networks-with-adaptive","title":"GeniePath: Graph Neural Networks with Adaptive Receptive Paths","arxiv_id":"1802.00910","date":"2018-02-03","proceeding":null,"authors":["Ziqi Liu","Chaochao Chen","Longfei Li","Jun Zhou","Xiaolong Li","Le Song","Yuan Qi"],"abstract":"We present, GeniePath, a scalable approach for learning adaptive receptive\nfields of neural networks defined on permutation invariant graph data. In\nGeniePath, we propose an adaptive path layer consists of two complementary\nfunctions designed for breadth and depth exploration respectively, where the\nformer learns the importance of different sized neighborhoods, while the latter\nextracts and filters signals aggregated from neighbors of different hops away.\nOur method works in both transductive and inductive settings, and extensive\nexperiments compared with competitive methods show that our approaches yield\nstate-of-the-art results on large graphs.","url_abs":"http://arxiv.org/abs/1802.00910v3","url_pdf":"http://arxiv.org/pdf/1802.00910v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"geniepath-graph-neural-networks-with-adaptive","repo_url":"https://github.com/shawnwang-tech/GeniePath-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"geniepath-graph-neural-networks-with-adaptive","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/geniepath","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"geniepath-graph-neural-networks-with-adaptive","repo_url":"https://github.com/safe-graph/DGFraud/tree/master/algorithms/GeniePath","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"geniepath","method_name":"GeniePath"}],"datasets_introduced":[],"methods_introduced":[{"slug":"geniepath","name":"GeniePath","full_name":"GeniePath"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.00910","atlas_url":"https://app.syntology.ai/?focus=1802.00910","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}