{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/scalable-graph-neural-networks-for-1","title":"Scalable Graph Neural Networks for Heterogeneous Graphs","arxiv_id":"2011.09679","date":"2020-11-19","proceeding":null,"authors":["Lingfan Yu","Jiajun Shen","Jinyang Li","Adam Lerer"],"abstract":"Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks by simply operating on graph-smoothed node features, rather than using end-to-end learned feature hierarchies that are challenging to scale to large graphs. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities. We propose Neighbor Averaging over Relation Subgraphs (NARS), which trains a classifier on neighbor-averaged features for randomly-sampled subgraphs of the \"metagraph\" of relations. We describe optimizations to allow these sets of node features to be computed in a memory-efficient way, both at training and inference time. NARS achieves a new state of the art accuracy on several benchmark datasets, outperforming more expensive GNN-based methods","url_abs":"https://arxiv.org/abs/2011.09679v1","url_pdf":"https://arxiv.org/pdf/2011.09679v1.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":"scalable-graph-neural-networks-for-1","repo_url":"https://github.com/facebookresearch/NARS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"heterogeneous-node-classification","task_name":"Heterogeneous Node Classification"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/heterogeneous-node-classification-on-acm","task":"Heterogeneous Node Classification","dataset":"ACM (Heterogeneous Node Classification)","model":"NARS","rank_in_archive_order":4,"of":11,"metrics":{" Macro-F1":"93.36","Micro-F1":"93.31"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-2","task":"Heterogeneous Node Classification","dataset":"DBLP (Heterogeneous Node Classification)","model":"NARS","rank_in_archive_order":3,"of":11,"metrics":{" Macro-F1":"94.18","Micro-F1":"94.61"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-freebase","task":"Heterogeneous Node Classification","dataset":"Freebase (Heterogeneous Node Classification)","model":"NARS","rank_in_archive_order":2,"of":9,"metrics":{" Macro-F1":"49.98","Micro-F1":"63.26"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-imdb","task":"Heterogeneous Node Classification","dataset":"IMDB (Heterogeneous Node Classification)","model":"NARS","rank_in_archive_order":4,"of":11,"metrics":{" Macro-F1":"63.51","Micro-F1":"66.18"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-oag-l1","task":"Heterogeneous Node Classification","dataset":"OAG-L1-Field","model":"NARS","rank_in_archive_order":2,"of":5,"metrics":{"MRR":"85.15","NDCG":"86.06"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-oag","task":"Heterogeneous Node Classification","dataset":"OAG-Venue","model":"NARS","rank_in_archive_order":2,"of":5,"metrics":{"MRR":"34.38","NDCG":"52.28"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-mag","task":"Node Property Prediction","dataset":"ogbn-mag","model":"NARS","rank_in_archive_order":22,"of":39,"metrics":{"Ext. data":"No","Number of params":"4130149","Test Accuracy":"0.5240 ± 0.0016","Validation Accuracy":"0.5372 ± 0.0009"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.09679","atlas_url":"https://app.syntology.ai/?focus=2011.09679","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2011.09679"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2011.09679\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2011.09679"},"call":"get_concepts_for_paper(arxiv_id=\"2011.09679\")"}],"by_repo":[{"repo":"facebookresearch/NARS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"96aa6ce057ce4fe101afd96ffc306be73d721bcc6a92b5e6131d3a4a326b26c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}