{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2SEHKPDAF6KKWY4R765EQAAYZH","short_pith_number":"pith:2SEHKPDA","schema_version":"1.0","canonical_sha256":"d488753c602f94ab6391ffba480018c9e3d0998fcede42978b83215700525435","source":{"kind":"arxiv","id":"2407.05005","version":2},"attestation_state":"computed","paper":{"title":"Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Haozhao Wang, Jingcai Guo, Ruixuan Li, Wenchao Xu, Yichen Li, Yining Qi","submitted_at":"2024-07-06T08:57:22Z","abstract_excerpt":"This paper focuses on Federated Domain-Incremental Learning (FDIL) where each client continues to learn incremental tasks where their domain shifts from each other. We propose a novel adaptive knowledge matching-based personalized FDIL approach (pFedDIL) which allows each client to alternatively utilize appropriate incremental task learning strategy on the correlation with the knowledge from previous tasks. More specifically, when a new task arrives, each client first calculates its local correlations with previous tasks. Then, the client can choose to adopt a new initial model or a previous m"},"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":"2407.05005","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-06T08:57:22Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"edb6c8dbd046e1d8df63ca58e80c6bc56811b21ae0dfd27e16127ebe5aa72ceb","abstract_canon_sha256":"6a3c4a9cbb694ace7cee672ef9d8100c988365d64ab734ad90d33b5839ee0381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:30.451536Z","signature_b64":"pPHqs8s7kH7ht8vYP2cJqM84o+2sGxDOYd7GAVoifqX3hVcyBGVjIheSDn+zx4vVKJ22qHVvs7MtWGBZrQ/CAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d488753c602f94ab6391ffba480018c9e3d0998fcede42978b83215700525435","last_reissued_at":"2026-07-05T08:45:30.450882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:30.450882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Haozhao Wang, Jingcai Guo, Ruixuan Li, Wenchao Xu, Yichen Li, Yining Qi","submitted_at":"2024-07-06T08:57:22Z","abstract_excerpt":"This paper focuses on Federated Domain-Incremental Learning (FDIL) where each client continues to learn incremental tasks where their domain shifts from each other. We propose a novel adaptive knowledge matching-based personalized FDIL approach (pFedDIL) which allows each client to alternatively utilize appropriate incremental task learning strategy on the correlation with the knowledge from previous tasks. More specifically, when a new task arrives, each client first calculates its local correlations with previous tasks. Then, the client can choose to adopt a new initial model or a previous m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05005","kind":"arxiv","version":2},"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/2407.05005/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":"2407.05005","created_at":"2026-07-05T08:45:30.450935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05005v2","created_at":"2026-07-05T08:45:30.450935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05005","created_at":"2026-07-05T08:45:30.450935+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SEHKPDAF6KK","created_at":"2026-07-05T08:45:30.450935+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SEHKPDAF6KKWY4R","created_at":"2026-07-05T08:45:30.450935+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SEHKPDA","created_at":"2026-07-05T08:45:30.450935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13840","citing_title":"Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey","ref_index":101,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH","json":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH.json","graph_json":"https://pith.science/api/pith-number/2SEHKPDAF6KKWY4R765EQAAYZH/graph.json","events_json":"https://pith.science/api/pith-number/2SEHKPDAF6KKWY4R765EQAAYZH/events.json","paper":"https://pith.science/paper/2SEHKPDA"},"agent_actions":{"view_html":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH","download_json":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH.json","view_paper":"https://pith.science/paper/2SEHKPDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05005&json=true","fetch_graph":"https://pith.science/api/pith-number/2SEHKPDAF6KKWY4R765EQAAYZH/graph.json","fetch_events":"https://pith.science/api/pith-number/2SEHKPDAF6KKWY4R765EQAAYZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH/action/storage_attestation","attest_author":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH/action/author_attestation","sign_citation":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH/action/citation_signature","submit_replication":"https://pith.science/pith/2SEHKPDAF6KKWY4R765EQAAYZH/action/replication_record"}},"created_at":"2026-07-05T08:45:30.450935+00:00","updated_at":"2026-07-05T08:45:30.450935+00:00"}