{"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/just-jump-dynamic-neighborhood-aggregation-in","title":"Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks","arxiv_id":"1904.04849","date":"2019-04-09","proceeding":null,"authors":["Matthias Fey"],"abstract":"We propose a dynamic neighborhood aggregation (DNA) procedure guided by\n(multi-head) attention for representation learning on graphs. In contrast to\ncurrent graph neural networks which follow a simple neighborhood aggregation\nscheme, our DNA procedure allows for a selective and node-adaptive aggregation\nof neighboring embeddings of potentially differing locality. In order to avoid\noverfitting, we propose to control the channel-wise connections between input\nand output by making use of grouped linear projections. In a number of\ntransductive node-classification experiments, we demonstrate the effectiveness\nof our approach.","url_abs":"http://arxiv.org/abs/1904.04849v2","url_pdf":"http://arxiv.org/pdf/1904.04849v2.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":"just-jump-dynamic-neighborhood-aggregation-in","repo_url":"https://github.com/rusty1s/pytorch_geometric","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"DNAConv","rank_in_archive_order":27,"of":71,"metrics":{"Accuracy":"74.50%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.04849","atlas_url":"https://app.syntology.ai/?focus=1904.04849","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}