{"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/representation-learning-on-graphs-with","title":"Representation Learning on Graphs with Jumping Knowledge Networks","arxiv_id":"1806.03536","date":"2018-06-09","proceeding":"ICML 2018 7","authors":["Keyulu Xu","Chengtao Li","Yonglong Tian","Tomohiro Sonobe","Ken-ichi Kawarabayashi","Stefanie Jegelka"],"abstract":"Recent deep learning approaches for representation learning on graphs follow\na neighborhood aggregation procedure. We analyze some important properties of\nthese models, and propose a strategy to overcome those. In particular, the\nrange of \"neighboring\" nodes that a node's representation draws from strongly\ndepends on the graph structure, analogous to the spread of a random walk. To\nadapt to local neighborhood properties and tasks, we explore an architecture --\njumping knowledge (JK) networks -- that flexibly leverages, for each node,\ndifferent neighborhood ranges to enable better structure-aware representation.\nIn a number of experiments on social, bioinformatics and citation networks, we\ndemonstrate that our model achieves state-of-the-art performance. Furthermore,\ncombining the JK framework with models like Graph Convolutional Networks,\nGraphSAGE and Graph Attention Networks consistently improves those models'\nperformance.","url_abs":"http://arxiv.org/abs/1806.03536v2","url_pdf":"http://arxiv.org/pdf/1806.03536v2.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":"representation-learning-on-graphs-with","repo_url":"https://github.com/mori97/JKNet-dgl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"representation-learning-on-graphs-with","repo_url":"https://github.com/shinkyuy/representation_learning_on_graphs_with_jumping_knowledge_networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"representation-learning-on-graphs-with","repo_url":"https://github.com/willy-b/tiny-GIN-for-ogbg-molhiv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"representation-learning-on-graphs-with","repo_url":"https://github.com/xnuohz/jknet-dgl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"representation-learning-on-graphs-with","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/jknet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"graph-convolutional-networks","method_name":"Graph Convolutional Networks"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-ppi","task":"Node Classification","dataset":"PPI","model":"JK-LSTM","rank_in_archive_order":14,"of":24,"metrics":{"F1":"97.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"JKNet (GCN-based)","rank_in_archive_order":66,"of":86,"metrics":{"Ext. data":"No","Number of params":"89000","Test Accuracy":"0.7219 ± 0.0021","Validation Accuracy":"0.7335 ± 0.0007"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.03536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.03536"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xnuohz/jknet-dgl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/jknet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/willy-b/tiny-GIN-for-ogbg-molhiv","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mori97/JKNet-dgl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shinkyuy/representation_learning_on_graphs_with_jumping_knowledge_networks","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ab0a016fefeb5192","entry":"evaluate","repo":"mori97/JKNet-dgl","repo_kind":"listed","path":"train_cora.py","file_url":"https://github.com/mori97/JKNet-dgl/blob/HEAD/train_cora.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab0a016fefeb5192"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}