{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QFYLEO7EJZJSW2V6CZ45LA2XEO","short_pith_number":"pith:QFYLEO7E","schema_version":"1.0","canonical_sha256":"8170b23be44e532b6abe1679d5835723bb0d8a5039b0ab72038eb1ac2d863f00","source":{"kind":"arxiv","id":"2504.17520","version":1},"attestation_state":"computed","paper":{"title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Mehdi Bennis, Yiwei Li, Zhaoyang Zhang, Zhuojun Tian","submitted_at":"2025-04-24T13:02:54Z","abstract_excerpt":"To jointly tackle the challenges of data and node heterogeneity in decentralized learning, we propose a distributed strong lottery ticket hypothesis (DSLTH), based on which a communication-efficient personalized learning algorithm is developed. In the proposed method, each local model is represented as the Hadamard product of global real-valued parameters and a personalized binary mask for pruning. The local model is learned by updating and fusing the personalized binary masks while the real-valued parameters are fixed among different agents. To further reduce the complexity of hardware implem"},"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":"2504.17520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-24T13:02:54Z","cross_cats_sorted":["cs.DC","cs.MA"],"title_canon_sha256":"10aa9a1572219578d975102f30b8dc5143faf2ee5cc4b71c4e5636d08e71f431","abstract_canon_sha256":"fc99da401eef10daa245a53ff83808e4466cc972a445ace23a71018f1e13b262"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:30.235778Z","signature_b64":"aPMW/UV5RpFUKQFnx/6JkzJbqqcjBUdmO3dw9E4AtjWkMGDHgDdnhg5I7NfgCOINQ1PR1ZK+oMPenwXO+euUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8170b23be44e532b6abe1679d5835723bb0d8a5039b0ab72038eb1ac2d863f00","last_reissued_at":"2026-07-05T10:53:30.235118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:30.235118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Mehdi Bennis, Yiwei Li, Zhaoyang Zhang, Zhuojun Tian","submitted_at":"2025-04-24T13:02:54Z","abstract_excerpt":"To jointly tackle the challenges of data and node heterogeneity in decentralized learning, we propose a distributed strong lottery ticket hypothesis (DSLTH), based on which a communication-efficient personalized learning algorithm is developed. In the proposed method, each local model is represented as the Hadamard product of global real-valued parameters and a personalized binary mask for pruning. The local model is learned by updating and fusing the personalized binary masks while the real-valued parameters are fixed among different agents. To further reduce the complexity of hardware implem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17520","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/2504.17520/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":"2504.17520","created_at":"2026-07-05T10:53:30.235190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17520v1","created_at":"2026-07-05T10:53:30.235190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17520","created_at":"2026-07-05T10:53:30.235190+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFYLEO7EJZJS","created_at":"2026-07-05T10:53:30.235190+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFYLEO7EJZJSW2V6","created_at":"2026-07-05T10:53:30.235190+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFYLEO7E","created_at":"2026-07-05T10:53:30.235190+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/QFYLEO7EJZJSW2V6CZ45LA2XEO","json":"https://pith.science/pith/QFYLEO7EJZJSW2V6CZ45LA2XEO.json","graph_json":"https://pith.science/api/pith-number/QFYLEO7EJZJSW2V6CZ45LA2XEO/graph.json","events_json":"https://pith.science/api/pith-number/QFYLEO7EJZJSW2V6CZ45LA2XEO/events.json","paper":"https://pith.science/paper/QFYLEO7E"},"agent_actions":{"view_html":"https://pith.science/pith/QFYLEO7EJZJSW2V6CZ45LA2XEO","download_json":"https://pith.science/pith/QFYLEO7EJZJSW2V6CZ45LA2XEO.json","view_paper":"https://pith.science/paper/QFYLEO7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17520&json=true","fetch_graph":"https://pith.science/api/pith-number/QFYLEO7EJZJSW2V6CZ45LA2XEO/graph.json","fetch_events":"https://pith.science/api/pith-number/QFYLEO7EJZJSW2V6CZ45LA2XEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFYLEO7EJZJSW2V6CZ45LA2XEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFYLEO7EJZJSW2V6CZ45LA2XEO/action/storage_attestation","attest_author":"https://pith.science/pith/QFYLEO7EJZJSW2V6CZ45LA2XEO/action/author_attestation","sign_citation":"https://pith.science/pith/QFYLEO7EJZJSW2V6CZ45LA2XEO/action/citation_signature","submit_replication":"https://pith.science/pith/QFYLEO7EJZJSW2V6CZ45LA2XEO/action/replication_record"}},"created_at":"2026-07-05T10:53:30.235190+00:00","updated_at":"2026-07-05T10:53:30.235190+00:00"}