{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B3CW43F3UDGLKYEDTJO2DV3JTD","short_pith_number":"pith:B3CW43F3","schema_version":"1.0","canonical_sha256":"0ec56e6cbba0ccb560839a5da1d76998dbd20ad85c22a235076a9855eab79598","source":{"kind":"arxiv","id":"2409.17189","version":1},"attestation_state":"computed","paper":{"title":"Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Angelia Nedich, Duong Thuy Anh Nguyen, Duong Tung Nguyen, H. Vincent Poor, Su Wang","submitted_at":"2024-09-25T06:23:16Z","abstract_excerpt":"We investigate the problem of agent-to-agent interaction in decentralized (federated) learning over time-varying directed graphs, and, in doing so, propose a consensus-based algorithm called DSGTm-TV. The proposed algorithm incorporates gradient tracking and heavy-ball momentum to distributively optimize a global objective function, while preserving local data privacy. Under DSGTm-TV, agents will update local model parameters and gradient estimates using information exchange with neighboring agents enabled through row- and column-stochastic mixing matrices, which we show guarantee both consens"},"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":"2409.17189","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2024-09-25T06:23:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"184a7050cec25b3ee1ec1f87148133e1d642898152b98afa1d727fa842ff3f4f","abstract_canon_sha256":"d91ecc202a261034e7ea534ce34830db64d5ec545b978e67722d041b5f96cd69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:49.501555Z","signature_b64":"UwqIwoBASgqfMG6elOht5xLb+ML2V7AYGtT43JBS5lVlbTSUGo0znYROfRNF5oKI9waXTXocnW/XiwViA9S5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ec56e6cbba0ccb560839a5da1d76998dbd20ad85c22a235076a9855eab79598","last_reissued_at":"2026-07-05T09:11:49.501162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:49.501162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Angelia Nedich, Duong Thuy Anh Nguyen, Duong Tung Nguyen, H. Vincent Poor, Su Wang","submitted_at":"2024-09-25T06:23:16Z","abstract_excerpt":"We investigate the problem of agent-to-agent interaction in decentralized (federated) learning over time-varying directed graphs, and, in doing so, propose a consensus-based algorithm called DSGTm-TV. The proposed algorithm incorporates gradient tracking and heavy-ball momentum to distributively optimize a global objective function, while preserving local data privacy. Under DSGTm-TV, agents will update local model parameters and gradient estimates using information exchange with neighboring agents enabled through row- and column-stochastic mixing matrices, which we show guarantee both consens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17189","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/2409.17189/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":"2409.17189","created_at":"2026-07-05T09:11:49.501236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17189v1","created_at":"2026-07-05T09:11:49.501236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17189","created_at":"2026-07-05T09:11:49.501236+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3CW43F3UDGL","created_at":"2026-07-05T09:11:49.501236+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3CW43F3UDGLKYED","created_at":"2026-07-05T09:11:49.501236+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3CW43F3","created_at":"2026-07-05T09:11:49.501236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06687","citing_title":"Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizers","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03442","citing_title":"Local Updates in Distributed Optimization: Provable Acceleration and Topology Effects","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD","json":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD.json","graph_json":"https://pith.science/api/pith-number/B3CW43F3UDGLKYEDTJO2DV3JTD/graph.json","events_json":"https://pith.science/api/pith-number/B3CW43F3UDGLKYEDTJO2DV3JTD/events.json","paper":"https://pith.science/paper/B3CW43F3"},"agent_actions":{"view_html":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD","download_json":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD.json","view_paper":"https://pith.science/paper/B3CW43F3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17189&json=true","fetch_graph":"https://pith.science/api/pith-number/B3CW43F3UDGLKYEDTJO2DV3JTD/graph.json","fetch_events":"https://pith.science/api/pith-number/B3CW43F3UDGLKYEDTJO2DV3JTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD/action/storage_attestation","attest_author":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD/action/author_attestation","sign_citation":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD/action/citation_signature","submit_replication":"https://pith.science/pith/B3CW43F3UDGLKYEDTJO2DV3JTD/action/replication_record"}},"created_at":"2026-07-05T09:11:49.501236+00:00","updated_at":"2026-07-05T09:11:49.501236+00:00"}