{"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/fused-gromov-wasserstein-graph-mixup-for-1","title":"Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications","arxiv_id":"2306.15963","date":"2023-06-28","proceeding":"NeurIPS 2023 11","authors":["Xinyu Ma","Xu Chu","Yasha Wang","Yang Lin","Junfeng Zhao","Liantao Ma","Wenwu Zhu"],"abstract":"Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph structure space independently, neglecting the joint interaction between them. In this paper, we address this limitation by formulating the problem as an optimal transport problem that aims to find an optimal inter-graph node matching strategy considering the interactions between graph structures and signals. To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a midpoint of source graphs in the Fused Gromov-Wasserstein (FGW) metric space. To enhance the scalability of our method, we introduce a relaxed FGW solver that accelerates FGWMixup by improving the convergence rate from $\\mathcal{O}(t^{-1})$ to $\\mathcal{O}(t^{-2})$. Extensive experiments conducted on five datasets using both classic (MPNNs) and advanced (Graphormers) GNN backbones demonstrate that FGWMixup effectively improves the generalizability and robustness of GNNs. Codes are available at https://github.com/ArthurLeoM/FGWMixup.","url_abs":"https://arxiv.org/abs/2306.15963v2","url_pdf":"https://arxiv.org/pdf/2306.15963v2.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":"fused-gromov-wasserstein-graph-mixup-for-1","repo_url":"https://github.com/arthurleom/fgwmixup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.15963","atlas_url":"https://app.syntology.ai/?focus=2306.15963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15963"}},"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":"deterministic:regex_extraction","url":"https://github.com/ArthurLeoM/FGWMixup","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arthurleom/fgwmixup","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"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":8,"samples":[{"code_sha256_prefix":"ff00a877e232a9f9","entry":"find_thresh","repo":"arthurleom/fgwmixup","repo_kind":"official","path":"src/gromov_mixup.py","file_url":"https://github.com/arthurleom/fgwmixup/blob/HEAD/src/gromov_mixup.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff00a877e232a9f9"}},{"code_sha256_prefix":"41a05f2d69abefee","entry":"mixup_cross_entropy_loss","repo":"arthurleom/fgwmixup","repo_kind":"official","path":"src/gmixup_dgl.py","file_url":"https://github.com/arthurleom/fgwmixup/blob/HEAD/src/gmixup_dgl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"41a05f2d69abefee"}},{"code_sha256_prefix":"8f07b4faace68a1e","entry":"prepare_dataset_onehot_y","repo":"arthurleom/fgwmixup","repo_kind":"official","path":"src/gmixup_dgl.py","file_url":"https://github.com/arthurleom/fgwmixup/blob/HEAD/src/gmixup_dgl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f07b4faace68a1e"}},{"code_sha256_prefix":"cd2b9d7aab3484d9","entry":"sp_to_adjency","repo":"arthurleom/fgwmixup","repo_kind":"official","path":"src/gromov_mixup.py","file_url":"https://github.com/arthurleom/fgwmixup/blob/HEAD/src/gromov_mixup.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd2b9d7aab3484d9"}},{"code_sha256_prefix":"798334f7fa9c3e30","entry":"FGWMixup","repo":"arthurleom/fgwmixup","repo_kind":"official","path":"src/gromov_mixup.py","file_url":"https://github.com/arthurleom/fgwmixup/blob/HEAD/src/gromov_mixup.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"798334f7fa9c3e30"}},{"code_sha256_prefix":"e5a45fb33e3d635c","entry":"fused_ACC_numpy","repo":"arthurleom/fgwmixup","repo_kind":"official","path":"src/gromov_mixup.py","file_url":"https://github.com/arthurleom/fgwmixup/blob/HEAD/src/gromov_mixup.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e5a45fb33e3d635c"}},{"code_sha256_prefix":"3e8ac7d25aef9917","entry":"my_fgw_barycenters","repo":"arthurleom/fgwmixup","repo_kind":"official","path":"src/gromov_mixup.py","file_url":"https://github.com/arthurleom/fgwmixup/blob/HEAD/src/gromov_mixup.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e8ac7d25aef9917"}},{"code_sha256_prefix":"8fa4bfa83d1f845f","entry":"prepare_dataset_x","repo":"arthurleom/fgwmixup","repo_kind":"official","path":"src/gmixup_dgl.py","file_url":"https://github.com/arthurleom/fgwmixup/blob/HEAD/src/gmixup_dgl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8fa4bfa83d1f845f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}