{"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/clarify-confused-nodes-through-separated","title":"Clarify Confused Nodes via Separated Learning","arxiv_id":"2306.02285","date":"2023-06-04","proceeding":null,"authors":["Jiajun Zhou","Shengbo Gong","Xuanze Chen","Chenxuan Xie","Shanqing Yu","Qi Xuan","Xiaoniu Yang"],"abstract":"Graph neural networks (GNNs) have achieved remarkable advances in graph-oriented tasks. However, real-world graphs invariably contain a certain proportion of heterophilous nodes, challenging the homophily assumption of traditional GNNs and hindering their performance. Most existing studies continue to design generic models with shared weights between heterophilous and homophilous nodes. Despite the incorporation of high-order messages or multi-channel architectures, these efforts often fall short. A minority of studies attempt to train different node groups separately but suffer from inappropriate separation metrics and low efficiency. In this paper, we first propose a new metric, termed Neighborhood Confusion (NC), to facilitate a more reliable separation of nodes. We observe that node groups with different levels of NC values exhibit certain differences in intra-group accuracy and visualized embeddings. These pave the way for Neighborhood Confusion-guided Graph Convolutional Network (NCGCN), in which nodes are grouped by their NC values and accept intra-group weight sharing and message passing. Extensive experiments on both homophilous and heterophilous benchmarks demonstrate that our framework can effectively separate nodes and yield significant performance improvement compared to the latest methods. The source code will be available in https://github.com/GISec-Team/NCGNN.","url_abs":"https://arxiv.org/abs/2306.02285v6","url_pdf":"https://arxiv.org/pdf/2306.02285v6.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":"clarify-confused-nodes-through-separated","repo_url":"https://github.com/GISec-Team/NCGNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-amz-computers","task":"Node Classification","dataset":"AMZ Computers","model":"NCGCN","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"90.81 ± 0.46"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amz-computers","task":"Node Classification","dataset":"AMZ Computers","model":"NCSAGE","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"90.43 ± 0.72"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amz-photo","task":"Node Classification","dataset":"AMZ Photo","model":"NCSAGE","rank_in_archive_order":1,"of":14,"metrics":{"Accuracy":"95.93 ± 0.36"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amz-photo","task":"Node Classification","dataset":"AMZ Photo","model":"NCGCN","rank_in_archive_order":3,"of":14,"metrics":{"Accuracy":"95.45 ± 0.45"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"NCSAGE","rank_in_archive_order":1,"of":62,"metrics":{"Accuracy":"43.89 ± 1.33"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"NCGCN","rank_in_archive_order":2,"of":62,"metrics":{"Accuracy":"43.16 ± 1.32"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon-60-20-20-1","task":"Node Classification","dataset":"Chameleon(60%/20%/20% random splits)","model":"NCSAGE","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"48.07 ± 3.47"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon-60-20-20-1","task":"Node Classification","dataset":"Chameleon(60%/20%/20% random splits)","model":"NCGCN","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"46.84 ± 4.36"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-cs","task":"Node Classification","dataset":"Coauthor CS","model":"NCGCN","rank_in_archive_order":1,"of":24,"metrics":{"Accuracy":"96.64 ± 0.29"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-cs","task":"Node Classification","dataset":"Coauthor CS","model":"NCSAGE","rank_in_archive_order":2,"of":24,"metrics":{"Accuracy":"96.48 ± 0.25"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-physics","task":"Node Classification","dataset":"Coauthor Physics","model":"NCSAGE","rank_in_archive_order":1,"of":14,"metrics":{"Accuracy":"98.69 ± 0.26"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-physics","task":"Node Classification","dataset":"Coauthor Physics","model":"NCGCN","rank_in_archive_order":2,"of":14,"metrics":{"Accuracy":"98.63 ± 0.24"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-full","task":"Node Classification","dataset":"Cora Full","model":"NCSAGE","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"72.58 ± 0.65%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-full-supervised","task":"Node Classification","dataset":"Cora Full-supervised","model":"NCGCN","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"73.42 ± 0.58%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-penn94","task":"Node Classification","dataset":"Penn94","model":"NCGCN","rank_in_archive_order":10,"of":32,"metrics":{"Accuracy":"84.74 ± 0.28"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-penn94","task":"Node Classification","dataset":"Penn94","model":"NCSAGE","rank_in_archive_order":17,"of":32,"metrics":{"Accuracy":"81.77 ± 0.71"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"NCGCN","rank_in_archive_order":1,"of":70,"metrics":{"Accuracy":"91.64 ± 0.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"NCSAGE","rank_in_archive_order":2,"of":70,"metrics":{"Accuracy":"91.55 ± 0.38"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-60-20-20-1","task":"Node Classification","dataset":"Squirrel(60%/20%/20% random splits)","model":"NCSAGE","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"54.42 ± 1.41"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-60-20-20-1","task":"Node Classification","dataset":"Squirrel(60%/20%/20% random splits)","model":"NCGCN","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"54.15 ± 1.47"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"GISec-Team/NCGNN","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":"28ae003fd0478f90b8f08db1050264b25678a411fd16acca6733d1109a20e6ec","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}