{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LK7X4YQT2EIFHXZ7Y5DCT7WO7O","short_pith_number":"pith:LK7X4YQT","schema_version":"1.0","canonical_sha256":"5abf7e6213d11053df3fc74629fecefb9729fa9210211445e90ecb1e8f44e85f","source":{"kind":"arxiv","id":"2110.12906","version":3},"attestation_state":"computed","paper":{"title":"Tackling the Local Bias in Federated Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Binchi Zhang, Jun Zhou, Minnan Luo, Qinghua Zheng, Shangbin Feng, Ziqi Liu","submitted_at":"2021-10-22T08:22:36Z","abstract_excerpt":"Federated graph learning (FGL) has become an important research topic in response to the increasing scale and the distributed nature of graph-structured data in the real world. In FGL, a global graph is distributed across different clients, where each client holds a subgraph. Existing FGL methods often fail to effectively utilize cross-client edges, losing structural information during the training; additionally, local graphs often exhibit significant distribution divergence. These two issues make local models in FGL less desirable than in centralized graph learning, namely the local bias prob"},"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":"2110.12906","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-22T08:22:36Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"9500b58e31737b4539789cb3fdaa83db83106d3ac5d7bc3b4032345b3396a54a","abstract_canon_sha256":"b4dbb5c2952e7f91c8a962ee796fdcaae1fd55440e3b8df21faa44cdaa2e673b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:38.787878Z","signature_b64":"9I9njeZG/u8rlEHUMTtDpaHKnEX3oEbmHUhQNue5rh32eQ9/EeZPw7l1EWqadcbdQKl8QDSCnkoRb2TpTcfgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5abf7e6213d11053df3fc74629fecefb9729fa9210211445e90ecb1e8f44e85f","last_reissued_at":"2026-07-05T08:58:38.784485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:38.784485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tackling the Local Bias in Federated Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Binchi Zhang, Jun Zhou, Minnan Luo, Qinghua Zheng, Shangbin Feng, Ziqi Liu","submitted_at":"2021-10-22T08:22:36Z","abstract_excerpt":"Federated graph learning (FGL) has become an important research topic in response to the increasing scale and the distributed nature of graph-structured data in the real world. In FGL, a global graph is distributed across different clients, where each client holds a subgraph. Existing FGL methods often fail to effectively utilize cross-client edges, losing structural information during the training; additionally, local graphs often exhibit significant distribution divergence. These two issues make local models in FGL less desirable than in centralized graph learning, namely the local bias prob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12906","kind":"arxiv","version":3},"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/2110.12906/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":"2110.12906","created_at":"2026-07-05T08:58:38.787327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12906v3","created_at":"2026-07-05T08:58:38.787327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12906","created_at":"2026-07-05T08:58:38.787327+00:00"},{"alias_kind":"pith_short_12","alias_value":"LK7X4YQT2EIF","created_at":"2026-07-05T08:58:38.787327+00:00"},{"alias_kind":"pith_short_16","alias_value":"LK7X4YQT2EIFHXZ7","created_at":"2026-07-05T08:58:38.787327+00:00"},{"alias_kind":"pith_short_8","alias_value":"LK7X4YQT","created_at":"2026-07-05T08:58:38.787327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08374","citing_title":"Federated Graph Learning with Graphless Clients","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O","json":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O.json","graph_json":"https://pith.science/api/pith-number/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/graph.json","events_json":"https://pith.science/api/pith-number/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/events.json","paper":"https://pith.science/paper/LK7X4YQT"},"agent_actions":{"view_html":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O","download_json":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O.json","view_paper":"https://pith.science/paper/LK7X4YQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12906&json=true","fetch_graph":"https://pith.science/api/pith-number/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/graph.json","fetch_events":"https://pith.science/api/pith-number/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/action/storage_attestation","attest_author":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/action/author_attestation","sign_citation":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/action/citation_signature","submit_replication":"https://pith.science/pith/LK7X4YQT2EIFHXZ7Y5DCT7WO7O/action/replication_record"}},"created_at":"2026-07-05T08:58:38.787327+00:00","updated_at":"2026-07-05T08:58:38.787327+00:00"}