{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4VDIFOV2N424P254ITUSWDNPTA","short_pith_number":"pith:4VDIFOV2","schema_version":"1.0","canonical_sha256":"e54682baba6f35c7ebbc44e92b0daf981d60c323a98d628dccf3d4b67c4f2ed2","source":{"kind":"arxiv","id":"2302.10911","version":4},"attestation_state":"computed","paper":{"title":"Revisiting Weighted Aggregation in Federated Learning with Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Wu, Tao Lin, Xinyi Shang, Zexi Li","submitted_at":"2023-02-14T07:52:21Z","abstract_excerpt":"In federated learning (FL), weighted aggregation of local models is conducted to generate a global model, and the aggregation weights are normalized (the sum of weights is 1) and proportional to the local data sizes. In this paper, we revisit the weighted aggregation process and gain new insights into the training dynamics of FL. First, we find that the sum of weights can be smaller than 1, causing global weight shrinking effect (analogous to weight decay) and improving generalization. We explore how the optimal shrinking factor is affected by clients' data heterogeneity and local epochs. Seco"},"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":"2302.10911","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-14T07:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"cb8ce018ba5ff677a4e5970fe696837d2c08ca2df22253f8a214f0e971ffc951","abstract_canon_sha256":"7e5c8cb0fc28ce8fb1f1afa7a097a83254ba724957e5780072cc61e9e39f1b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:39.497919Z","signature_b64":"DFXLIGJe5vV4MBCtlFvibRmgXdHIfvQ5x3C0dHtmrKhJHNRCXSkVayWc5T76zWe33dJ6RoPJTZfHcgFHPTNcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e54682baba6f35c7ebbc44e92b0daf981d60c323a98d628dccf3d4b67c4f2ed2","last_reissued_at":"2026-07-05T06:19:39.497356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:39.497356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Weighted Aggregation in Federated Learning with Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Wu, Tao Lin, Xinyi Shang, Zexi Li","submitted_at":"2023-02-14T07:52:21Z","abstract_excerpt":"In federated learning (FL), weighted aggregation of local models is conducted to generate a global model, and the aggregation weights are normalized (the sum of weights is 1) and proportional to the local data sizes. In this paper, we revisit the weighted aggregation process and gain new insights into the training dynamics of FL. First, we find that the sum of weights can be smaller than 1, causing global weight shrinking effect (analogous to weight decay) and improving generalization. We explore how the optimal shrinking factor is affected by clients' data heterogeneity and local epochs. Seco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10911","kind":"arxiv","version":4},"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/2302.10911/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":"2302.10911","created_at":"2026-07-05T06:19:39.497420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10911v4","created_at":"2026-07-05T06:19:39.497420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10911","created_at":"2026-07-05T06:19:39.497420+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VDIFOV2N424","created_at":"2026-07-05T06:19:39.497420+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VDIFOV2N424P254","created_at":"2026-07-05T06:19:39.497420+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VDIFOV2","created_at":"2026-07-05T06:19:39.497420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02982","citing_title":"MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA","json":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA.json","graph_json":"https://pith.science/api/pith-number/4VDIFOV2N424P254ITUSWDNPTA/graph.json","events_json":"https://pith.science/api/pith-number/4VDIFOV2N424P254ITUSWDNPTA/events.json","paper":"https://pith.science/paper/4VDIFOV2"},"agent_actions":{"view_html":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA","download_json":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA.json","view_paper":"https://pith.science/paper/4VDIFOV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10911&json=true","fetch_graph":"https://pith.science/api/pith-number/4VDIFOV2N424P254ITUSWDNPTA/graph.json","fetch_events":"https://pith.science/api/pith-number/4VDIFOV2N424P254ITUSWDNPTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA/action/storage_attestation","attest_author":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA/action/author_attestation","sign_citation":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA/action/citation_signature","submit_replication":"https://pith.science/pith/4VDIFOV2N424P254ITUSWDNPTA/action/replication_record"}},"created_at":"2026-07-05T06:19:39.497420+00:00","updated_at":"2026-07-05T06:19:39.497420+00:00"}