{"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/bertgcn-transductive-text-classification-by","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","arxiv_id":"2105.05727","date":"2021-05-12","proceeding":null,"authors":["Yuxiao Lin","Yuxian Meng","Xiaofei Sun","Qinghong Han","Kun Kuang","Jiwei Li","Fei Wu"],"abstract":"In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification. BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations. By jointly training the BERT and GCN modules within BertGCN, the proposed model is able to leverage the advantages of both worlds: large-scale pretraining which takes the advantage of the massive amount of raw data and transductive learning which jointly learns representations for both training data and unlabeled test data by propagating label influence through graph convolution. Experiments show that BertGCN achieves SOTA performances on a wide range of text classification datasets. Code is available at https://github.com/ZeroRin/BertGCN.","url_abs":"https://arxiv.org/abs/2105.05727v4","url_pdf":"https://arxiv.org/pdf/2105.05727v4.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":"bertgcn-transductive-text-classification-by","repo_url":"https://github.com/ZeroRin/BertGCN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"transductive-learning","task_name":"Transductive Learning"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-classification-on-20-newsgroups","task":"Text Classification","dataset":"20 Newsgroups","model":"RoBERTaGCN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"89.5"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-20news","task":"Text Classification","dataset":"20NEWS","model":"RoBERTaGCN","rank_in_archive_order":2,"of":16,"metrics":{"Accuracy":"89.5"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-mr","task":"Text Classification","dataset":"MR","model":"RoBERTaGCN","rank_in_archive_order":3,"of":10,"metrics":{"Accuracy":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-ohsumed","task":"Text Classification","dataset":"Ohsumed","model":"RoBERTaGCN","rank_in_archive_order":1,"of":10,"metrics":{"Accuracy":"72.8"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-r52","task":"Text Classification","dataset":"R52","model":"1-6 BertGCN","rank_in_archive_order":1,"of":8,"metrics":{"Accuracy":"96.6"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-r8","task":"Text Classification","dataset":"R8","model":"RoBERTaGCN","rank_in_archive_order":4,"of":21,"metrics":{"Accuracy":"98.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.05727","atlas_url":"https://app.syntology.ai/?focus=2105.05727","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":"2105.05727"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2105.05727\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2105.05727"},"call":"get_concepts_for_paper(arxiv_id=\"2105.05727\")"}],"by_repo":[{"repo":"ZeroRin/BertGCN","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":"4faedf660573a0e6cb4c49e54c881776838576896fef686b1db5527e3c9860f1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}