{"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/bag-of-tricks-of-semi-supervised","title":"Bag of Tricks for Node Classification with Graph Neural Networks","arxiv_id":"2103.13355","date":"2021-03-24","proceeding":null,"authors":["Yangkun Wang","Jiarui Jin","Weinan Zhang","Yong Yu","Zheng Zhang","David Wipf"],"abstract":"Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs. However, in addition to their reliance on elaborate architectures and algorithms, there are several key technical details that are frequently overlooked, and yet nonetheless can play a vital role in achieving satisfactory performance. In this paper, we first summarize a series of existing tricks-of-the-trade, and then propose several new ones related to label usage, loss function formulation, and model design that can significantly improve various GNN architectures. We empirically evaluate their impact on final node classification accuracy by conducting ablation studies and demonstrate consistently-improved performance, often to an extent that outweighs the gains from more dramatic changes in the underlying GNN architecture. Notably, many of the top-ranked models on the Open Graph Benchmark (OGB) leaderboard and KDDCUP 2021 Large-Scale Challenge MAG240M-LSC benefit from these techniques we initiated.","url_abs":"https://arxiv.org/abs/2103.13355v4","url_pdf":"https://arxiv.org/pdf/2103.13355v4.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":"bag-of-tricks-of-semi-supervised","repo_url":"https://github.com/espylapiza/Bag-of-Tricks-for-Node-Classification-with-Graph-Neural-Networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"bag-of-tricks-of-semi-supervised","repo_url":"https://github.com/orion-wyc/gaga","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"GAT+norm. adj.+label reuse","rank_in_archive_order":34,"of":86,"metrics":{"Ext. data":"No","Number of params":"1441580","Test Accuracy":"0.7391 ± 0.0012","Validation Accuracy":"0.7516 ± 0.0008"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"GAT+norm. adj.+labels","rank_in_archive_order":40,"of":86,"metrics":{"Ext. data":"No","Number of params":"1441580","Test Accuracy":"0.7366 ± 0.0011","Validation Accuracy":"0.7508 ± 0.0009"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"GAT+norm.adj.+labels","rank_in_archive_order":41,"of":86,"metrics":{"Ext. data":"No","Number of params":"1628440","Test Accuracy":"0.7365 ± 0.0011","Validation Accuracy":"0.7504 ± 0.0006"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"GCN+linear+labels","rank_in_archive_order":49,"of":86,"metrics":{"Ext. data":"No","Number of params":"238632","Test Accuracy":"0.7306 ± 0.0024","Validation Accuracy":"0.7442 ± 0.0012"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"GAT+BoT","rank_in_archive_order":7,"of":26,"metrics":{"Ext. data":"No","Number of params":"2484192","Test ROC-AUC":"0.8765 ± 0.0008","Validation ROC-AUC":"0.9280 ± 0.0008"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"GAT+EdgeFeatureAtt","rank_in_archive_order":11,"of":26,"metrics":{"Ext. data":"No","Number of params":"2475232","Test ROC-AUC":"0.8682 ± 0.0021","Validation ROC-AUC":"0.9194 ± 0.0003"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.13355","atlas_url":"https://app.syntology.ai/?focus=2103.13355","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":"2103.13355"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.13355\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.13355"},"call":"get_concepts_for_paper(arxiv_id=\"2103.13355\")"}],"by_repo":[{"repo":"espylapiza/Bag-of-Tricks-for-Node-Classification-with-Graph-Neural-Networks","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"orion-wyc/gaga","kind":"listed","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":"c50b31f2d0d65f10cb3e4f5d2298617626a3e4bfb0548127456d004ac297d0d8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}