{"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/optimal-transport-graph-neural-networks","title":"Optimal Transport Graph Neural Networks","arxiv_id":"2006.04804","date":"2020-06-08","proceeding":null,"authors":["Benson Chen","Gary Bécigneul","Octavian-Eugen Ganea","Regina Barzilay","Tommi Jaakkola"],"abstract":"Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation -- potentially losing structural or semantic information. We here introduce OT-GNN, a model that computes graph embeddings using parametric prototypes that highlight key facets of different graph aspects. Towards this goal, we successfully combine optimal transport (OT) with parametric graph models. Graph representations are obtained from Wasserstein distances between the set of GNN node embeddings and ``prototype'' point clouds as free parameters. We theoretically prove that, unlike traditional sum aggregation, our function class on point clouds satisfies a fundamental universal approximation theorem. Empirically, we address an inherent collapse optimization issue by proposing a noise contrastive regularizer to steer the model towards truly exploiting the OT geometry. Finally, we outperform popular methods on several molecular property prediction tasks, while exhibiting smoother graph representations.","url_abs":"https://arxiv.org/abs/2006.04804v6","url_pdf":"https://arxiv.org/pdf/2006.04804v6.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":"optimal-transport-graph-neural-networks","repo_url":"https://github.com/benatorc/OTGNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"optimal-transport-graph-neural-networks","repo_url":"https://github.com/jbr-ai-labs/lipophilicity-prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/drug-discovery-on-bace","task":"Drug Discovery","dataset":"BACE","model":"ProtoW-L2","rank_in_archive_order":3,"of":6,"metrics":{"AUC":"0.873"},"uses_additional_data":false},{"leaderboard":"/sota/drug-discovery-on-bbbp","task":"Drug Discovery","dataset":"BBBP","model":"ProtoW-L2","rank_in_archive_order":1,"of":4,"metrics":{"AUC":"0.92"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-esol","task":"Graph Regression","dataset":"ESOL","model":"ProtoW-dot","rank_in_archive_order":1,"of":1,"metrics":{"RMSE":".594"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-lipophilicity","task":"Graph Regression","dataset":"Lipophilicity","model":"ProtoS-L2","rank_in_archive_order":9,"of":23,"metrics":{"RMSE":"0.580"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.04804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04804"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/benatorc/OTGNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jbr-ai-labs/lipophilicity-prediction","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":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":1,"samples":[{"code_sha256_prefix":"14907279b1e6ca98","entry":"reshape_tensor_to_bond_list","repo":"benatorc/OTGNN","repo_kind":"official","path":"train_proto.py","file_url":"https://github.com/benatorc/OTGNN/blob/HEAD/train_proto.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"14907279b1e6ca98"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}