{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/data-augmentation-for-graph-neural-networks","title":"Data Augmentation for Graph Neural Networks","arxiv_id":"2006.06830","date":"2020-06-11","proceeding":null,"authors":["Tong Zhao","Yozen Liu","Leonardo Neves","Oliver Woodford","Meng Jiang","Neil Shah"],"abstract":"Data augmentation has been widely used to improve generalizability of machine learning models. However, comparatively little work studies data augmentation for graphs. This is largely due to the complex, non-Euclidean structure of graphs, which limits possible manipulation operations. Augmentation operations commonly used in vision and language have no analogs for graphs. Our work studies graph data augmentation for graph neural networks (GNNs) in the context of improving semi-supervised node-classification. We discuss practical and theoretical motivations, considerations and strategies for graph data augmentation. Our work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra-class edges and demote inter-class edges in given graph structure, and our main contribution introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction. Extensive experiments on multiple benchmarks show that augmentation via GAug improves performance across GNN architectures and datasets.","url_abs":"https://arxiv.org/abs/2006.06830v2","url_pdf":"https://arxiv.org/pdf/2006.06830v2.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":"data-augmentation-for-graph-neural-networks","repo_url":"https://github.com/zhao-tong/GAug","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"data-augmentation-for-graph-neural-networks","repo_url":"https://github.com/andyjzhao/wsdm23-gsr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-blogcatalog-1","task":"Node Classification","dataset":"BlogCatalog","model":"GCN+GAugM","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"77.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-with-public","task":"Node Classification","dataset":"CiteSeer with Public Split: fixed 20 nodes per class","model":"GCN+GAugO","rank_in_archive_order":19,"of":40,"metrics":{"Accuracy":"73.3 ± 1.1"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-with-public-split","task":"Node Classification","dataset":"Cora with Public Split: fixed 20 nodes per class","model":"GCN+GAugO","rank_in_archive_order":16,"of":36,"metrics":{"Accuracy":"83.6 ± 0.5%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-flickr","task":"Node Classification","dataset":"Flickr","model":"GCN+GAugM (Zhao et al., 2021)","rank_in_archive_order":1,"of":8,"metrics":{"Accuracy":"0.682"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.06830","atlas_url":"https://app.syntology.ai/?focus=2006.06830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06830"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhao-tong/GAug","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andyjzhao/wsdm23-gsr","reach":{"status":"ok"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2730ce09ffb06fd1","entry":"sample_graph_det","repo":"zhao-tong/GAug","repo_kind":"official","path":"train_GAugM.py","file_url":"https://github.com/zhao-tong/GAug/blob/HEAD/train_GAugM.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2730ce09ffb06fd1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}