{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNY6KM6GU5WMQZ3EES7B3A7EFD","short_pith_number":"pith:FNY6KM6G","schema_version":"1.0","canonical_sha256":"2b71e533c6a76cc8676424be1d83e428ea0f7778f4bc8d6db2494ef2db901c7d","source":{"kind":"arxiv","id":"2412.13442","version":1},"attestation_state":"computed","paper":{"title":"Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Can Ma, Rong Yin, Ruyue Liu, Weiping Wang, Xiangzhen Bo, Xiaoshuai Hao, Xingrui Zhou, Yong Liu","submitted_at":"2024-12-18T02:26:07Z","abstract_excerpt":"Federated graph learning (FGL) has gained significant attention for enabling heterogeneous clients to process their private graph data locally while interacting with a centralized server, thus maintaining privacy. However, graph data on clients are typically non-IID, posing a challenge for a single model to perform well across all clients. Another major bottleneck of FGL is the high cost of communication. To address these challenges, we propose a communication-efficient personalized federated graph learning algorithm, CEFGL. Our method decomposes the model parameters into low-rank generic and "},"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":"2412.13442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T02:26:07Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"7ce646b7215a3c4bda3141d5d9e21e1cc84e63439095edd6c5f11c58a6c814f5","abstract_canon_sha256":"ec070f56727fc1b395aaca9d1e1271493adbbbe6b780452939dd544c0a27fc20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:01.869812Z","signature_b64":"4TSbTphcd9yG6RCzcNJi65FImkU9YtrDWtPK8NKAZXq+YoUpKkxOcg4J78/AR1435p6odbslsOMfphAeLiJoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b71e533c6a76cc8676424be1d83e428ea0f7778f4bc8d6db2494ef2db901c7d","last_reissued_at":"2026-07-05T09:51:01.869308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:01.869308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Can Ma, Rong Yin, Ruyue Liu, Weiping Wang, Xiangzhen Bo, Xiaoshuai Hao, Xingrui Zhou, Yong Liu","submitted_at":"2024-12-18T02:26:07Z","abstract_excerpt":"Federated graph learning (FGL) has gained significant attention for enabling heterogeneous clients to process their private graph data locally while interacting with a centralized server, thus maintaining privacy. However, graph data on clients are typically non-IID, posing a challenge for a single model to perform well across all clients. Another major bottleneck of FGL is the high cost of communication. To address these challenges, we propose a communication-efficient personalized federated graph learning algorithm, CEFGL. Our method decomposes the model parameters into low-rank generic and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13442","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/2412.13442/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":"2412.13442","created_at":"2026-07-05T09:51:01.869379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13442v1","created_at":"2026-07-05T09:51:01.869379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13442","created_at":"2026-07-05T09:51:01.869379+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNY6KM6GU5WM","created_at":"2026-07-05T09:51:01.869379+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNY6KM6GU5WMQZ3E","created_at":"2026-07-05T09:51:01.869379+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNY6KM6G","created_at":"2026-07-05T09:51:01.869379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09805","citing_title":"Federated Learning with Graph-Based Aggregation for Traffic Forecasting","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD","json":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD.json","graph_json":"https://pith.science/api/pith-number/FNY6KM6GU5WMQZ3EES7B3A7EFD/graph.json","events_json":"https://pith.science/api/pith-number/FNY6KM6GU5WMQZ3EES7B3A7EFD/events.json","paper":"https://pith.science/paper/FNY6KM6G"},"agent_actions":{"view_html":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD","download_json":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD.json","view_paper":"https://pith.science/paper/FNY6KM6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13442&json=true","fetch_graph":"https://pith.science/api/pith-number/FNY6KM6GU5WMQZ3EES7B3A7EFD/graph.json","fetch_events":"https://pith.science/api/pith-number/FNY6KM6GU5WMQZ3EES7B3A7EFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD/action/storage_attestation","attest_author":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD/action/author_attestation","sign_citation":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD/action/citation_signature","submit_replication":"https://pith.science/pith/FNY6KM6GU5WMQZ3EES7B3A7EFD/action/replication_record"}},"created_at":"2026-07-05T09:51:01.869379+00:00","updated_at":"2026-07-05T09:51:01.869379+00:00"}