{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LDXUJZNCRZSL37ZPOWKGY6IUJH","short_pith_number":"pith:LDXUJZNC","schema_version":"1.0","canonical_sha256":"58ef44e5a28e64bdff2f75946c791449dcb8e749c6916801b987a8b0f8c126e5","source":{"kind":"arxiv","id":"2206.06818","version":1},"attestation_state":"computed","paper":{"title":"Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Tieniu Tan, Yunlong Wang, Zhenan Sun, Zhengquan Luo, Zilei Wang","submitted_at":"2022-06-14T13:12:12Z","abstract_excerpt":"Attributes skew hinders the current federated learning (FL) frameworks from consistent optimization directions among the clients, which inevitably leads to performance reduction and unstable convergence. The core problems lie in that: 1) Domain-specific attributes, which are non-causal and only locally valid, are indeliberately mixed into global aggregation. 2) The one-stage optimizations of entangled attributes cannot simultaneously satisfy two conflicting objectives, i.e., generalization and personalization. To cope with these, we proposed disentangled federated learning (DFL) to disentangle"},"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":"2206.06818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T13:12:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b12c8163fbdc583595d3745e031a39f663fec2d2474f336bb6af6a3a1ab1539","abstract_canon_sha256":"a3e909f578ed5eaf152f19815137199d60325d788685a8e2451bbdf4bce6ebac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:46.089626Z","signature_b64":"s01AMkPi2m1UP7FhzX2brBQe0AaQk3P0llp1D0x1Ub3P5sfaQtYFXZTkvbt32RLAf0FGVE4ldR55N7z1XxzbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ef44e5a28e64bdff2f75946c791449dcb8e749c6916801b987a8b0f8c126e5","last_reissued_at":"2026-07-05T04:31:46.089211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:46.089211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Tieniu Tan, Yunlong Wang, Zhenan Sun, Zhengquan Luo, Zilei Wang","submitted_at":"2022-06-14T13:12:12Z","abstract_excerpt":"Attributes skew hinders the current federated learning (FL) frameworks from consistent optimization directions among the clients, which inevitably leads to performance reduction and unstable convergence. The core problems lie in that: 1) Domain-specific attributes, which are non-causal and only locally valid, are indeliberately mixed into global aggregation. 2) The one-stage optimizations of entangled attributes cannot simultaneously satisfy two conflicting objectives, i.e., generalization and personalization. To cope with these, we proposed disentangled federated learning (DFL) to disentangle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06818","kind":"arxiv","version":1},"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/2206.06818/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":"2206.06818","created_at":"2026-07-05T04:31:46.089268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06818v1","created_at":"2026-07-05T04:31:46.089268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06818","created_at":"2026-07-05T04:31:46.089268+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDXUJZNCRZSL","created_at":"2026-07-05T04:31:46.089268+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDXUJZNCRZSL37ZP","created_at":"2026-07-05T04:31:46.089268+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDXUJZNC","created_at":"2026-07-05T04:31:46.089268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04979","citing_title":"Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH","json":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH.json","graph_json":"https://pith.science/api/pith-number/LDXUJZNCRZSL37ZPOWKGY6IUJH/graph.json","events_json":"https://pith.science/api/pith-number/LDXUJZNCRZSL37ZPOWKGY6IUJH/events.json","paper":"https://pith.science/paper/LDXUJZNC"},"agent_actions":{"view_html":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH","download_json":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH.json","view_paper":"https://pith.science/paper/LDXUJZNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06818&json=true","fetch_graph":"https://pith.science/api/pith-number/LDXUJZNCRZSL37ZPOWKGY6IUJH/graph.json","fetch_events":"https://pith.science/api/pith-number/LDXUJZNCRZSL37ZPOWKGY6IUJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH/action/storage_attestation","attest_author":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH/action/author_attestation","sign_citation":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH/action/citation_signature","submit_replication":"https://pith.science/pith/LDXUJZNCRZSL37ZPOWKGY6IUJH/action/replication_record"}},"created_at":"2026-07-05T04:31:46.089268+00:00","updated_at":"2026-07-05T04:31:46.089268+00:00"}