{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HKPVQAS7YUHRD7SAKN5CPPWCFX","short_pith_number":"pith:HKPVQAS7","schema_version":"1.0","canonical_sha256":"3a9f58025fc50f11fe40537a27bec22de3101b209215f0ca2effd20b38959f87","source":{"kind":"arxiv","id":"2201.11380","version":1},"attestation_state":"computed","paper":{"title":"Achieving Personalized Federated Learning with Sparse Local Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Fengxiang He, Li Shen, Shiwei Liu, Tiansheng Huang, Weiwei Lin","submitted_at":"2022-01-27T08:43:11Z","abstract_excerpt":"Federated learning (FL) is vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user. To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user. However, PFL is far from its maturity, because existing PFL solutions either demonstrate unsatisfactory generalization towards different model architectures or cost enormous extra computation and memory. In this work, we propose federated learning with personalized sparse mask (FedSpa), a novel PFL scheme"},"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":"2201.11380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T08:43:11Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"dc88a0fa4f56769310efd937c69bb873f5fe4df6f639f021d39a3b5537b1751e","abstract_canon_sha256":"56123430a732fe262b9c6ed65bd9dc79ccd771709d19bc012c31c19c21dcba88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:01.848679Z","signature_b64":"BlVEsMHm4zZuPz7EnKdkKgM4EmkUz1knpJL428s7rY1/8yr+sdgVKcewci3zWHNAo9HCZNfUzilHmb8uY9YkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a9f58025fc50f11fe40537a27bec22de3101b209215f0ca2effd20b38959f87","last_reissued_at":"2026-07-05T03:52:01.848145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:01.848145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving Personalized Federated Learning with Sparse Local Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Fengxiang He, Li Shen, Shiwei Liu, Tiansheng Huang, Weiwei Lin","submitted_at":"2022-01-27T08:43:11Z","abstract_excerpt":"Federated learning (FL) is vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user. To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user. However, PFL is far from its maturity, because existing PFL solutions either demonstrate unsatisfactory generalization towards different model architectures or cost enormous extra computation and memory. In this work, we propose federated learning with personalized sparse mask (FedSpa), a novel PFL scheme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11380","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/2201.11380/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":"2201.11380","created_at":"2026-07-05T03:52:01.848264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11380v1","created_at":"2026-07-05T03:52:01.848264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11380","created_at":"2026-07-05T03:52:01.848264+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKPVQAS7YUHR","created_at":"2026-07-05T03:52:01.848264+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKPVQAS7YUHRD7SA","created_at":"2026-07-05T03:52:01.848264+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKPVQAS7","created_at":"2026-07-05T03:52:01.848264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX","json":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX.json","graph_json":"https://pith.science/api/pith-number/HKPVQAS7YUHRD7SAKN5CPPWCFX/graph.json","events_json":"https://pith.science/api/pith-number/HKPVQAS7YUHRD7SAKN5CPPWCFX/events.json","paper":"https://pith.science/paper/HKPVQAS7"},"agent_actions":{"view_html":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX","download_json":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX.json","view_paper":"https://pith.science/paper/HKPVQAS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11380&json=true","fetch_graph":"https://pith.science/api/pith-number/HKPVQAS7YUHRD7SAKN5CPPWCFX/graph.json","fetch_events":"https://pith.science/api/pith-number/HKPVQAS7YUHRD7SAKN5CPPWCFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX/action/storage_attestation","attest_author":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX/action/author_attestation","sign_citation":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX/action/citation_signature","submit_replication":"https://pith.science/pith/HKPVQAS7YUHRD7SAKN5CPPWCFX/action/replication_record"}},"created_at":"2026-07-05T03:52:01.848264+00:00","updated_at":"2026-07-05T03:52:01.848264+00:00"}