{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LKRXSWNHF6P53BUIYH2A5CZCJI","short_pith_number":"pith:LKRXSWNH","schema_version":"1.0","canonical_sha256":"5aa37959a72f9fdd8688c1f40e8b224a051af71da8a5893a59f2ef16294ee9dc","source":{"kind":"arxiv","id":"2203.09249","version":2},"attestation_state":"computed","paper":{"title":"Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Liang Ding, Ling-Yu Duan, Lin Zhang, Li Shen","submitted_at":"2022-03-17T11:18:17Z","abstract_excerpt":"Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. Data heterogeneity is one of the main challenges in FL, which results in slow convergence and degraded performance. Most existing approaches only tackle the heterogeneity challenge by restricting the local model update in client, ignoring the performance drop caused by direct global model aggregation. Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation. Concretely, FedFTG explores the "},"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":"2203.09249","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-17T11:18:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7727e8ee1694a5e296bc788fea343a49ac275298abb805c3461534fdb4d42a3b","abstract_canon_sha256":"fe1ee6a0f8063be4fd0cf51c9c8f58e14df0633a062774e6f30127a4ee6f0738"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:04.432688Z","signature_b64":"dXW8jprRb42xLgu2aHxCHmfqB4VYLrs85/bTwW5ykk/M9EfTbB7lB0ot4isaFG0rtYTNLAIcman09AXy/K/lDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aa37959a72f9fdd8688c1f40e8b224a051af71da8a5893a59f2ef16294ee9dc","last_reissued_at":"2026-07-05T07:05:04.432125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:04.432125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Liang Ding, Ling-Yu Duan, Lin Zhang, Li Shen","submitted_at":"2022-03-17T11:18:17Z","abstract_excerpt":"Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. Data heterogeneity is one of the main challenges in FL, which results in slow convergence and degraded performance. Most existing approaches only tackle the heterogeneity challenge by restricting the local model update in client, ignoring the performance drop caused by direct global model aggregation. Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation. Concretely, FedFTG explores the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09249","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/2203.09249/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":"2203.09249","created_at":"2026-07-05T07:05:04.432185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09249v2","created_at":"2026-07-05T07:05:04.432185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09249","created_at":"2026-07-05T07:05:04.432185+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKRXSWNHF6P5","created_at":"2026-07-05T07:05:04.432185+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKRXSWNHF6P53BUI","created_at":"2026-07-05T07:05:04.432185+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKRXSWNH","created_at":"2026-07-05T07:05:04.432185+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/LKRXSWNHF6P53BUIYH2A5CZCJI","json":"https://pith.science/pith/LKRXSWNHF6P53BUIYH2A5CZCJI.json","graph_json":"https://pith.science/api/pith-number/LKRXSWNHF6P53BUIYH2A5CZCJI/graph.json","events_json":"https://pith.science/api/pith-number/LKRXSWNHF6P53BUIYH2A5CZCJI/events.json","paper":"https://pith.science/paper/LKRXSWNH"},"agent_actions":{"view_html":"https://pith.science/pith/LKRXSWNHF6P53BUIYH2A5CZCJI","download_json":"https://pith.science/pith/LKRXSWNHF6P53BUIYH2A5CZCJI.json","view_paper":"https://pith.science/paper/LKRXSWNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09249&json=true","fetch_graph":"https://pith.science/api/pith-number/LKRXSWNHF6P53BUIYH2A5CZCJI/graph.json","fetch_events":"https://pith.science/api/pith-number/LKRXSWNHF6P53BUIYH2A5CZCJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKRXSWNHF6P53BUIYH2A5CZCJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKRXSWNHF6P53BUIYH2A5CZCJI/action/storage_attestation","attest_author":"https://pith.science/pith/LKRXSWNHF6P53BUIYH2A5CZCJI/action/author_attestation","sign_citation":"https://pith.science/pith/LKRXSWNHF6P53BUIYH2A5CZCJI/action/citation_signature","submit_replication":"https://pith.science/pith/LKRXSWNHF6P53BUIYH2A5CZCJI/action/replication_record"}},"created_at":"2026-07-05T07:05:04.432185+00:00","updated_at":"2026-07-05T07:05:04.432185+00:00"}