{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MT24PQUDTCZFSUSMOIGGKB36C6","short_pith_number":"pith:MT24PQUD","schema_version":"1.0","canonical_sha256":"64f5c7c28398b259524c720c65077e17b9e5a79bdfab766e2d2edc76def765ed","source":{"kind":"arxiv","id":"2407.19389","version":3},"attestation_state":"computed","paper":{"title":"FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.DC","authors_text":"Feijie Wu, Jing Gao, Lu Su, Tianci Liu, Xingchen Wang, Yaqing Wang","submitted_at":"2024-07-28T04:10:11Z","abstract_excerpt":"In federated learning (FL), accommodating clients' varied computational capacities poses a challenge, often limiting the participation of those with constrained resources in global model training. To address this issue, the concept of model heterogeneity through submodel extraction has emerged, offering a tailored solution that aligns the model's complexity with each client's computational capacity. In this work, we propose Federated Importance-Aware Submodel Extraction (FIARSE), a novel approach that dynamically adjusts submodels based on the importance of model parameters, thereby overcoming"},"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":"2407.19389","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-07-28T04:10:11Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"34bcd80e6a7c291807ff31902501e8f086dd9fdf2ecba0f9adc70f3b4c48efe3","abstract_canon_sha256":"5994bd9346431213d221b2316f40157e57034a5e8337767615464f42d5dda5d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:29.533716Z","signature_b64":"55k3U7mPtl140APhxCubeRYj50cen1Rz/YYDnZg8cTyb6/kukewEWJNgzbrkVgMGLttZbgIydNNxDkGnrU4cDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64f5c7c28398b259524c720c65077e17b9e5a79bdfab766e2d2edc76def765ed","last_reissued_at":"2026-07-05T09:46:29.533161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:29.533161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.DC","authors_text":"Feijie Wu, Jing Gao, Lu Su, Tianci Liu, Xingchen Wang, Yaqing Wang","submitted_at":"2024-07-28T04:10:11Z","abstract_excerpt":"In federated learning (FL), accommodating clients' varied computational capacities poses a challenge, often limiting the participation of those with constrained resources in global model training. To address this issue, the concept of model heterogeneity through submodel extraction has emerged, offering a tailored solution that aligns the model's complexity with each client's computational capacity. In this work, we propose Federated Importance-Aware Submodel Extraction (FIARSE), a novel approach that dynamically adjusts submodels based on the importance of model parameters, thereby overcoming"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19389","kind":"arxiv","version":3},"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/2407.19389/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":"2407.19389","created_at":"2026-07-05T09:46:29.533233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19389v3","created_at":"2026-07-05T09:46:29.533233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19389","created_at":"2026-07-05T09:46:29.533233+00:00"},{"alias_kind":"pith_short_12","alias_value":"MT24PQUDTCZF","created_at":"2026-07-05T09:46:29.533233+00:00"},{"alias_kind":"pith_short_16","alias_value":"MT24PQUDTCZFSUSM","created_at":"2026-07-05T09:46:29.533233+00:00"},{"alias_kind":"pith_short_8","alias_value":"MT24PQUD","created_at":"2026-07-05T09:46:29.533233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.05372","citing_title":"Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6","json":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6.json","graph_json":"https://pith.science/api/pith-number/MT24PQUDTCZFSUSMOIGGKB36C6/graph.json","events_json":"https://pith.science/api/pith-number/MT24PQUDTCZFSUSMOIGGKB36C6/events.json","paper":"https://pith.science/paper/MT24PQUD"},"agent_actions":{"view_html":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6","download_json":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6.json","view_paper":"https://pith.science/paper/MT24PQUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19389&json=true","fetch_graph":"https://pith.science/api/pith-number/MT24PQUDTCZFSUSMOIGGKB36C6/graph.json","fetch_events":"https://pith.science/api/pith-number/MT24PQUDTCZFSUSMOIGGKB36C6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6/action/storage_attestation","attest_author":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6/action/author_attestation","sign_citation":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6/action/citation_signature","submit_replication":"https://pith.science/pith/MT24PQUDTCZFSUSMOIGGKB36C6/action/replication_record"}},"created_at":"2026-07-05T09:46:29.533233+00:00","updated_at":"2026-07-05T09:46:29.533233+00:00"}