{"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/label-deconvolution-for-node-representation","title":"Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias","arxiv_id":"2309.14907","date":"2023-09-26","proceeding":null,"authors":["Zhihao Shi","Jie Wang","Fanghua Lu","Hanzhu Chen","Defu Lian","Zheng Wang","Jieping Ye","Feng Wu"],"abstract":"Node representation learning on attributed graphs -- whose nodes are associated with rich attributes (e.g., texts and protein sequences) -- plays a crucial role in many important downstream tasks. To encode the attributes and graph structures simultaneously, recent studies integrate pre-trained models with graph neural networks (GNNs), where pre-trained models serve as node encoders (NEs) to encode the attributes. As jointly training large NEs and GNNs on large-scale graphs suffers from severe scalability issues, many methods propose to train NEs and GNNs separately. Consequently, they do not take feature convolutions in GNNs into consideration in the training phase of NEs, leading to a significant learning bias from that by the joint training. To address this challenge, we propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias. More importantly, we show that LD converges to the optimal objective function values by thejoint training under mild assumptions. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.","url_abs":"https://arxiv.org/abs/2309.14907v1","url_pdf":"https://arxiv.org/pdf/2309.14907v1.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":"label-deconvolution-for-node-representation","repo_url":"https://github.com/MIRALab-USTC/LD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"LD+REVGAT","rank_in_archive_order":5,"of":86,"metrics":{"Ext. data":"Yes","Number of params":"140438868","Test Accuracy":"0.7726 ± 0.0017","Validation Accuracy":"0.7762 ± 0.0008"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"LD+GIANT+SAGN+SCR","rank_in_archive_order":4,"of":64,"metrics":{"Ext. data":"Yes","Number of params":"110636896","Test Accuracy":"0.8718 ± 0.0004","Validation Accuracy":"0.9399 ± 0.0002"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"LD+GAMLP","rank_in_archive_order":11,"of":64,"metrics":{"Ext. data":"Yes","Number of params":"144331677","Test Accuracy":"0.8645 ± 0.0012","Validation Accuracy":"0.9415 ± 0.0003"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"LD+GAT","rank_in_archive_order":1,"of":26,"metrics":{"Ext. data":"Yes","Number of params":"664233700","Test ROC-AUC":"0.8942 ± 0.0007","Validation ROC-AUC":"0.9527 ± 0.0007"},"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":"MIRALab-USTC/LD","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":"8c527647bdc4098a6258c73fb3075ddbab61c6154a67e5aaf9d5a60820124e75","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}