{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RCLPCXOQZY4FS6VDWMJ65TWEPU","short_pith_number":"pith:RCLPCXOQ","schema_version":"1.0","canonical_sha256":"8896f15dd0ce38597aa3b313eecec47d12cb46113f2695c9807613afbf25cff5","source":{"kind":"arxiv","id":"2505.23176","version":2},"attestation_state":"computed","paper":{"title":"The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Haozhao Wang, Ruixuan Li, Shijie Xu, Shiwei Li, Weihong Luo, Xiandi Luo, Xing Tang, Xiuqiang He, Yuhua Li","submitted_at":"2025-05-29T07:14:32Z","abstract_excerpt":"To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we seek to enhance the performance of these low-rank decomposition methods. Specifically, we focus on three key issues related to decomposition in FL: what to decompose, how to decompose, and how to aggregate. Subsequently, we introduce three novel techniques: Model Update Decomposition (MUD), Block-wise Kronecker Decomposition (BKD), and Aggregation-Aware Decomposition (AAD), each targeting a specific issue. These tech"},"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":"2505.23176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T07:14:32Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"d4a339de04b73f6bd4b670ff22fc702d21e9cf3cdb05ba0a35373a611e6abb74","abstract_canon_sha256":"083f10d1fb0e5720bfbc10bf7cfeb88064f07a8f1a1cd226fc5cd912c912c7e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:47.628621Z","signature_b64":"d9ud9JmoX1ljsRNX4k3QeJjdXGtcw/n1YQKIABjuluraAFbmRYkcVvbOWIgT1hLjpgVhEev7vNRBP6jcq4LFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8896f15dd0ce38597aa3b313eecec47d12cb46113f2695c9807613afbf25cff5","last_reissued_at":"2026-07-05T11:54:47.628123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:47.628123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Haozhao Wang, Ruixuan Li, Shijie Xu, Shiwei Li, Weihong Luo, Xiandi Luo, Xing Tang, Xiuqiang He, Yuhua Li","submitted_at":"2025-05-29T07:14:32Z","abstract_excerpt":"To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we seek to enhance the performance of these low-rank decomposition methods. Specifically, we focus on three key issues related to decomposition in FL: what to decompose, how to decompose, and how to aggregate. Subsequently, we introduce three novel techniques: Model Update Decomposition (MUD), Block-wise Kronecker Decomposition (BKD), and Aggregation-Aware Decomposition (AAD), each targeting a specific issue. These tech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23176","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/2505.23176/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":"2505.23176","created_at":"2026-07-05T11:54:47.628181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23176v2","created_at":"2026-07-05T11:54:47.628181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23176","created_at":"2026-07-05T11:54:47.628181+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCLPCXOQZY4F","created_at":"2026-07-05T11:54:47.628181+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCLPCXOQZY4FS6VD","created_at":"2026-07-05T11:54:47.628181+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCLPCXOQ","created_at":"2026-07-05T11:54:47.628181+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/RCLPCXOQZY4FS6VDWMJ65TWEPU","json":"https://pith.science/pith/RCLPCXOQZY4FS6VDWMJ65TWEPU.json","graph_json":"https://pith.science/api/pith-number/RCLPCXOQZY4FS6VDWMJ65TWEPU/graph.json","events_json":"https://pith.science/api/pith-number/RCLPCXOQZY4FS6VDWMJ65TWEPU/events.json","paper":"https://pith.science/paper/RCLPCXOQ"},"agent_actions":{"view_html":"https://pith.science/pith/RCLPCXOQZY4FS6VDWMJ65TWEPU","download_json":"https://pith.science/pith/RCLPCXOQZY4FS6VDWMJ65TWEPU.json","view_paper":"https://pith.science/paper/RCLPCXOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23176&json=true","fetch_graph":"https://pith.science/api/pith-number/RCLPCXOQZY4FS6VDWMJ65TWEPU/graph.json","fetch_events":"https://pith.science/api/pith-number/RCLPCXOQZY4FS6VDWMJ65TWEPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCLPCXOQZY4FS6VDWMJ65TWEPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCLPCXOQZY4FS6VDWMJ65TWEPU/action/storage_attestation","attest_author":"https://pith.science/pith/RCLPCXOQZY4FS6VDWMJ65TWEPU/action/author_attestation","sign_citation":"https://pith.science/pith/RCLPCXOQZY4FS6VDWMJ65TWEPU/action/citation_signature","submit_replication":"https://pith.science/pith/RCLPCXOQZY4FS6VDWMJ65TWEPU/action/replication_record"}},"created_at":"2026-07-05T11:54:47.628181+00:00","updated_at":"2026-07-05T11:54:47.628181+00:00"}