{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CW4ISMSNVOB5JZWIVZ5QIQPHKD","short_pith_number":"pith:CW4ISMSN","schema_version":"1.0","canonical_sha256":"15b889324dab83d4e6c8ae7b0441e750df2b8f3b1e40a4a6a09d7640d70dc2b0","source":{"kind":"arxiv","id":"2411.19798","version":1},"attestation_state":"computed","paper":{"title":"Rethinking the initialization of Momentum in Federated Learning with Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenguang Xiao, Shuo Wang","submitted_at":"2024-11-29T16:00:52Z","abstract_excerpt":"Data Heterogeneity is a major challenge of Federated Learning performance. Recently, momentum based optimization techniques have beed proved to be effective in mitigating the heterogeneity issue. Along with the model updates, the momentum updates are transmitted to the server side and aggregated. Therefore, the local training initialized with a global momentum is guided by the global history of the gradients. However, we spot a problem in the traditional cumulation of the momentum which is suboptimal in the Federated Learning systems. The momentum used to weight less on the historical gradient"},"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":"2411.19798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T16:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"dcb37940c7bee7736d0ffe973bb9728ffb0efb2463bdd5662575f21e37cbb488","abstract_canon_sha256":"b1cf05e9cd7189c6242dd5eaaecae82d2087e7788232eb5388b61aebbbb5542b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:08.278052Z","signature_b64":"mpMqlOPZphRBGC5Jt5dz5PrGZ9oBxWuVJn9iTDiPZwdwKDFmt3MGkinHnrTupr4kbc8KyRBsZ1UxXS+H6YxSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15b889324dab83d4e6c8ae7b0441e750df2b8f3b1e40a4a6a09d7640d70dc2b0","last_reissued_at":"2026-07-05T09:42:08.277353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:08.277353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the initialization of Momentum in Federated Learning with Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenguang Xiao, Shuo Wang","submitted_at":"2024-11-29T16:00:52Z","abstract_excerpt":"Data Heterogeneity is a major challenge of Federated Learning performance. Recently, momentum based optimization techniques have beed proved to be effective in mitigating the heterogeneity issue. Along with the model updates, the momentum updates are transmitted to the server side and aggregated. Therefore, the local training initialized with a global momentum is guided by the global history of the gradients. However, we spot a problem in the traditional cumulation of the momentum which is suboptimal in the Federated Learning systems. The momentum used to weight less on the historical gradient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19798","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/2411.19798/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":"2411.19798","created_at":"2026-07-05T09:42:08.277418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19798v1","created_at":"2026-07-05T09:42:08.277418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19798","created_at":"2026-07-05T09:42:08.277418+00:00"},{"alias_kind":"pith_short_12","alias_value":"CW4ISMSNVOB5","created_at":"2026-07-05T09:42:08.277418+00:00"},{"alias_kind":"pith_short_16","alias_value":"CW4ISMSNVOB5JZWI","created_at":"2026-07-05T09:42:08.277418+00:00"},{"alias_kind":"pith_short_8","alias_value":"CW4ISMSN","created_at":"2026-07-05T09:42:08.277418+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/CW4ISMSNVOB5JZWIVZ5QIQPHKD","json":"https://pith.science/pith/CW4ISMSNVOB5JZWIVZ5QIQPHKD.json","graph_json":"https://pith.science/api/pith-number/CW4ISMSNVOB5JZWIVZ5QIQPHKD/graph.json","events_json":"https://pith.science/api/pith-number/CW4ISMSNVOB5JZWIVZ5QIQPHKD/events.json","paper":"https://pith.science/paper/CW4ISMSN"},"agent_actions":{"view_html":"https://pith.science/pith/CW4ISMSNVOB5JZWIVZ5QIQPHKD","download_json":"https://pith.science/pith/CW4ISMSNVOB5JZWIVZ5QIQPHKD.json","view_paper":"https://pith.science/paper/CW4ISMSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19798&json=true","fetch_graph":"https://pith.science/api/pith-number/CW4ISMSNVOB5JZWIVZ5QIQPHKD/graph.json","fetch_events":"https://pith.science/api/pith-number/CW4ISMSNVOB5JZWIVZ5QIQPHKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CW4ISMSNVOB5JZWIVZ5QIQPHKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CW4ISMSNVOB5JZWIVZ5QIQPHKD/action/storage_attestation","attest_author":"https://pith.science/pith/CW4ISMSNVOB5JZWIVZ5QIQPHKD/action/author_attestation","sign_citation":"https://pith.science/pith/CW4ISMSNVOB5JZWIVZ5QIQPHKD/action/citation_signature","submit_replication":"https://pith.science/pith/CW4ISMSNVOB5JZWIVZ5QIQPHKD/action/replication_record"}},"created_at":"2026-07-05T09:42:08.277418+00:00","updated_at":"2026-07-05T09:42:08.277418+00:00"}