{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ODVQ64GWAXRBBTFX2E3OXROMDA","short_pith_number":"pith:ODVQ64GW","schema_version":"1.0","canonical_sha256":"70eb0f70d605e210ccb7d136ebc5cc180c20b7ae3751284ecdcf6abe2eb3c1e7","source":{"kind":"arxiv","id":"2603.01730","version":2},"attestation_state":"computed","paper":{"title":"Decentralized Federated Learning by Partial Message Exchange","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Geoffrey Ye Li, Lingchen Kong, Shan Sha, Shenglong Zhou, Xin Wang","submitted_at":"2026-03-02T10:57:18Z","abstract_excerpt":"Decentralized federated learning (DFL) has emerged as a transformative server-free paradigm that enables collaborative learning over large-scale heterogeneous networks. However, it continues to face fundamental challenges, including data heterogeneity, restrictive assumptions for theoretical analysis, and degraded convergence when standard communication- or privacyenhancing techniques are applied. To overcome these drawbacks, this paper develops a novel algorithm, PaME (DFL by Partial Message Exchange). The central principle is to allow only randomly selected sparse coordinates to be exchanged"},"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":"2603.01730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-02T10:57:18Z","cross_cats_sorted":[],"title_canon_sha256":"b766715f136f0cc264252a02eb397022a2323d5e9be0de208e23c616b1112593","abstract_canon_sha256":"4c4855bb02149b79e73e15fd7558b229a1fbe60a65c446dd7dc55acb916cd316"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:48.634099Z","signature_b64":"zwMs7CONekivgOj9offziB6X5S3jR0EW1wr9yPvTUAmmQH9md/g25tdZgrY0ahcmppXlIcmp6pURc6NRhdMIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70eb0f70d605e210ccb7d136ebc5cc180c20b7ae3751284ecdcf6abe2eb3c1e7","last_reissued_at":"2026-07-07T02:19:48.633192Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:48.633192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Federated Learning by Partial Message Exchange","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Geoffrey Ye Li, Lingchen Kong, Shan Sha, Shenglong Zhou, Xin Wang","submitted_at":"2026-03-02T10:57:18Z","abstract_excerpt":"Decentralized federated learning (DFL) has emerged as a transformative server-free paradigm that enables collaborative learning over large-scale heterogeneous networks. However, it continues to face fundamental challenges, including data heterogeneity, restrictive assumptions for theoretical analysis, and degraded convergence when standard communication- or privacyenhancing techniques are applied. To overcome these drawbacks, this paper develops a novel algorithm, PaME (DFL by Partial Message Exchange). The central principle is to allow only randomly selected sparse coordinates to be exchanged"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.01730","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/2603.01730/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":"2603.01730","created_at":"2026-07-07T02:19:48.633307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.01730v2","created_at":"2026-07-07T02:19:48.633307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.01730","created_at":"2026-07-07T02:19:48.633307+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODVQ64GWAXRB","created_at":"2026-07-07T02:19:48.633307+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODVQ64GWAXRBBTFX","created_at":"2026-07-07T02:19:48.633307+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODVQ64GW","created_at":"2026-07-07T02:19:48.633307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00173","citing_title":"TallyTrain: Communication-Efficient Federated Distillation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA","json":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA.json","graph_json":"https://pith.science/api/pith-number/ODVQ64GWAXRBBTFX2E3OXROMDA/graph.json","events_json":"https://pith.science/api/pith-number/ODVQ64GWAXRBBTFX2E3OXROMDA/events.json","paper":"https://pith.science/paper/ODVQ64GW"},"agent_actions":{"view_html":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA","download_json":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA.json","view_paper":"https://pith.science/paper/ODVQ64GW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.01730&json=true","fetch_graph":"https://pith.science/api/pith-number/ODVQ64GWAXRBBTFX2E3OXROMDA/graph.json","fetch_events":"https://pith.science/api/pith-number/ODVQ64GWAXRBBTFX2E3OXROMDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA/action/storage_attestation","attest_author":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA/action/author_attestation","sign_citation":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA/action/citation_signature","submit_replication":"https://pith.science/pith/ODVQ64GWAXRBBTFX2E3OXROMDA/action/replication_record"}},"created_at":"2026-07-07T02:19:48.633307+00:00","updated_at":"2026-07-07T02:19:48.633307+00:00"}