{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:D4IK5W6NDRM52LCBGZ7NJHYNII","short_pith_number":"pith:D4IK5W6N","schema_version":"1.0","canonical_sha256":"1f10aedbcd1c59dd2c41367ed49f0d423464452ed29a922f1dfb998deb96609e","source":{"kind":"arxiv","id":"2012.13063","version":2},"attestation_state":"computed","paper":{"title":"Decentralized Federated Learning via Mutual Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Chengxi Li, Gang Li, Pramod K. Varshney","submitted_at":"2020-12-24T01:43:53Z","abstract_excerpt":"In this paper, we investigate the problem of decentralized federated learning (DFL) in Internet of things (IoT) systems, where a number of IoT clients train models collectively for a common task without sharing their private training data in the absence of a central server. Most of the existing DFL schemes are composed of two alternating steps, i.e., model updating and model averaging. However, averaging model parameters directly to fuse different models at the local clients suffers from client-drift especially when the training data are heterogeneous across different clients. This leads to sl"},"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":"2012.13063","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-24T01:43:53Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"652faf41528d45ae55446e417b341e499f003c959eee3d0f342e013f9298e863","abstract_canon_sha256":"224bb433ed9761ceb53ed8a63732ab4d0cba4c5776ae235dea2ba60c23eec467"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:43.704759Z","signature_b64":"ozRkXzzJ5wOcusFy9X2Bv1yytae/VmKDfhSJT7NiazGUILqntPWx7bBkQp0OPlrh7bfQF0gZo8qvn0lUEST5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f10aedbcd1c59dd2c41367ed49f0d423464452ed29a922f1dfb998deb96609e","last_reissued_at":"2026-07-05T02:39:43.704277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:43.704277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Federated Learning via Mutual Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Chengxi Li, Gang Li, Pramod K. Varshney","submitted_at":"2020-12-24T01:43:53Z","abstract_excerpt":"In this paper, we investigate the problem of decentralized federated learning (DFL) in Internet of things (IoT) systems, where a number of IoT clients train models collectively for a common task without sharing their private training data in the absence of a central server. Most of the existing DFL schemes are composed of two alternating steps, i.e., model updating and model averaging. However, averaging model parameters directly to fuse different models at the local clients suffers from client-drift especially when the training data are heterogeneous across different clients. This leads to sl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.13063","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/2012.13063/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":"2012.13063","created_at":"2026-07-05T02:39:43.704349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.13063v2","created_at":"2026-07-05T02:39:43.704349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.13063","created_at":"2026-07-05T02:39:43.704349+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4IK5W6NDRM5","created_at":"2026-07-05T02:39:43.704349+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4IK5W6NDRM52LCB","created_at":"2026-07-05T02:39:43.704349+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4IK5W6N","created_at":"2026-07-05T02:39:43.704349+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/D4IK5W6NDRM52LCBGZ7NJHYNII","json":"https://pith.science/pith/D4IK5W6NDRM52LCBGZ7NJHYNII.json","graph_json":"https://pith.science/api/pith-number/D4IK5W6NDRM52LCBGZ7NJHYNII/graph.json","events_json":"https://pith.science/api/pith-number/D4IK5W6NDRM52LCBGZ7NJHYNII/events.json","paper":"https://pith.science/paper/D4IK5W6N"},"agent_actions":{"view_html":"https://pith.science/pith/D4IK5W6NDRM52LCBGZ7NJHYNII","download_json":"https://pith.science/pith/D4IK5W6NDRM52LCBGZ7NJHYNII.json","view_paper":"https://pith.science/paper/D4IK5W6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.13063&json=true","fetch_graph":"https://pith.science/api/pith-number/D4IK5W6NDRM52LCBGZ7NJHYNII/graph.json","fetch_events":"https://pith.science/api/pith-number/D4IK5W6NDRM52LCBGZ7NJHYNII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4IK5W6NDRM52LCBGZ7NJHYNII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4IK5W6NDRM52LCBGZ7NJHYNII/action/storage_attestation","attest_author":"https://pith.science/pith/D4IK5W6NDRM52LCBGZ7NJHYNII/action/author_attestation","sign_citation":"https://pith.science/pith/D4IK5W6NDRM52LCBGZ7NJHYNII/action/citation_signature","submit_replication":"https://pith.science/pith/D4IK5W6NDRM52LCBGZ7NJHYNII/action/replication_record"}},"created_at":"2026-07-05T02:39:43.704349+00:00","updated_at":"2026-07-05T02:39:43.704349+00:00"}