{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4E5EMIVZUNOATKKLPLNQA3EQW7","short_pith_number":"pith:4E5EMIVZ","schema_version":"1.0","canonical_sha256":"e13a4622b9a35c09a94b7adb006c90b7f9e2d743176fec825d11ccb91e41fcfa","source":{"kind":"arxiv","id":"1905.10674","version":4},"attestation_state":"computed","paper":{"title":"Compositional Fairness Constraints for Graph Embeddings","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Avishek Joey Bose, William L. Hamilton","submitted_at":"2019-05-25T21:13:27Z","abstract_excerpt":"Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems. However, existing graph embedding techniques are unable to cope with fairness constraints, e.g., ensuring that the learned representations do not correlate with certain attributes, such as age or gender. Here, we introduce an adversarial framework to enforce fairness constraints on graph embeddings. Our approach is compositional---meaning that it can flexibly accommodate different combinations of fairness constraints during infer"},"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":"1905.10674","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-25T21:13:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"512fbee3663e86cb3f27ec3dd1971b9433efccaef5c07e8658ada73a69f97c83","abstract_canon_sha256":"09d66d638e0c315a5442623f04ce558d25eb42197dd95e780e742f4ddf5fd689"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:23.219803Z","signature_b64":"LDTO2TtLCtHFeXhpEPKaCnsospa5pAtHSgAFFTfEp6wIgTxSuNltwDafJOmuFheLbHUhXmpjCw+H+zH/JXeSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e13a4622b9a35c09a94b7adb006c90b7f9e2d743176fec825d11ccb91e41fcfa","last_reissued_at":"2026-05-17T23:40:23.219217Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:23.219217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Fairness Constraints for Graph Embeddings","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Avishek Joey Bose, William L. Hamilton","submitted_at":"2019-05-25T21:13:27Z","abstract_excerpt":"Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems. However, existing graph embedding techniques are unable to cope with fairness constraints, e.g., ensuring that the learned representations do not correlate with certain attributes, such as age or gender. Here, we introduce an adversarial framework to enforce fairness constraints on graph embeddings. Our approach is compositional---meaning that it can flexibly accommodate different combinations of fairness constraints during infer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10674","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1905.10674","created_at":"2026-05-17T23:40:23.219297+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10674v4","created_at":"2026-05-17T23:40:23.219297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10674","created_at":"2026-05-17T23:40:23.219297+00:00"},{"alias_kind":"pith_short_12","alias_value":"4E5EMIVZUNOA","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4E5EMIVZUNOATKKL","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4E5EMIVZ","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7","json":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7.json","graph_json":"https://pith.science/api/pith-number/4E5EMIVZUNOATKKLPLNQA3EQW7/graph.json","events_json":"https://pith.science/api/pith-number/4E5EMIVZUNOATKKLPLNQA3EQW7/events.json","paper":"https://pith.science/paper/4E5EMIVZ"},"agent_actions":{"view_html":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7","download_json":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7.json","view_paper":"https://pith.science/paper/4E5EMIVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10674&json=true","fetch_graph":"https://pith.science/api/pith-number/4E5EMIVZUNOATKKLPLNQA3EQW7/graph.json","fetch_events":"https://pith.science/api/pith-number/4E5EMIVZUNOATKKLPLNQA3EQW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7/action/storage_attestation","attest_author":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7/action/author_attestation","sign_citation":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7/action/citation_signature","submit_replication":"https://pith.science/pith/4E5EMIVZUNOATKKLPLNQA3EQW7/action/replication_record"}},"created_at":"2026-05-17T23:40:23.219297+00:00","updated_at":"2026-05-17T23:40:23.219297+00:00"}