{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XPYQI5FQ6LT65M4KO2K2ZXCQ3O","short_pith_number":"pith:XPYQI5FQ","schema_version":"1.0","canonical_sha256":"bbf10474b0f2e7eeb38a7695acdc50dba0644f7c85d95b910c8f03b75ba21067","source":{"kind":"arxiv","id":"2006.04804","version":6},"attestation_state":"computed","paper":{"title":"Optimal Transport Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benson Chen, Gary B\\'ecigneul, Octavian-Eugen Ganea, Regina Barzilay, Tommi Jaakkola","submitted_at":"2020-06-08T14:57:39Z","abstract_excerpt":"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 pr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.04804","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-08T14:57:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a12212bd451d58c193ca60ece5a35b56aa6992cb5385cb05b2fd4c946d3fa97d","abstract_canon_sha256":"9aa6494e3d21afffc99eb5792a7f846d7894e2387131fda9ffcda4cdac986d76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:05.621253Z","signature_b64":"YMd56AT4Yu9eG8NNuSUKzgew612WxKgB1jnI4d0RGP1dkOQOOq4kq9J0fFYXsGC6FWhGw2ANlEOczo0YONz2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbf10474b0f2e7eeb38a7695acdc50dba0644f7c85d95b910c8f03b75ba21067","last_reissued_at":"2026-07-05T03:21:05.620818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:05.620818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Transport Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benson Chen, Gary B\\'ecigneul, Octavian-Eugen Ganea, Regina Barzilay, Tommi Jaakkola","submitted_at":"2020-06-08T14:57:39Z","abstract_excerpt":"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 pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04804","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.04804/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.04804","created_at":"2026-07-05T03:21:05.620889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04804v6","created_at":"2026-07-05T03:21:05.620889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04804","created_at":"2026-07-05T03:21:05.620889+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPYQI5FQ6LT6","created_at":"2026-07-05T03:21:05.620889+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPYQI5FQ6LT65M4K","created_at":"2026-07-05T03:21:05.620889+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPYQI5FQ","created_at":"2026-07-05T03:21:05.620889+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27931","citing_title":"DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2404.15261","citing_title":"Resistance Distance and Linearized Optimal Transport on Graphs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2501.17443","citing_title":"Gradual Domain Adaptation for Graph Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O","json":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O.json","graph_json":"https://pith.science/api/pith-number/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/graph.json","events_json":"https://pith.science/api/pith-number/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/events.json","paper":"https://pith.science/paper/XPYQI5FQ"},"agent_actions":{"view_html":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O","download_json":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O.json","view_paper":"https://pith.science/paper/XPYQI5FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04804&json=true","fetch_graph":"https://pith.science/api/pith-number/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/graph.json","fetch_events":"https://pith.science/api/pith-number/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/action/storage_attestation","attest_author":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/action/author_attestation","sign_citation":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/action/citation_signature","submit_replication":"https://pith.science/pith/XPYQI5FQ6LT65M4KO2K2ZXCQ3O/action/replication_record"}},"created_at":"2026-07-05T03:21:05.620889+00:00","updated_at":"2026-07-05T03:21:05.620889+00:00"}