{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HLRGM3GVV4LSAKXHCDWL6E4HTA","short_pith_number":"pith:HLRGM3GV","schema_version":"1.0","canonical_sha256":"3ae2666cd5af17202ae710ecbf1387983b6f2e5ea47a961710b0b8169363c7b0","source":{"kind":"arxiv","id":"2605.26243","version":1},"attestation_state":"computed","paper":{"title":"Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Chen, Lei Zhang, Olivera Kotevska, Ravi K Madduri, Wenhan Wu, Zhishuai Guo","submitted_at":"2026-05-25T18:10:20Z","abstract_excerpt":"Graph neural networks (GNNs) achieve strong performance on relational data, but real-world graphs are often distributed across organizations that cannot share raw data due to privacy and policy constraints. Existing federated GNN methods either ignore cross-client links, leading to degraded accuracy, or require frequent embedding exchanges, incurring substantial communication and privacy costs. We propose CE-FedGNN, a communication-efficient and privacy-preserving federated GNN framework for learning over such coupled graphs. Our approach avoids sharing raw data or per-round embeddings by infr"},"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":"2605.26243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T18:10:20Z","cross_cats_sorted":[],"title_canon_sha256":"dfe9dc778cc975be78df1db2121120c6e26c17c5b688ad696d7834e4f0445e3f","abstract_canon_sha256":"fa63943ddbcf73e9a62600f997a1c802b207bea18776610f067b95eacb1d18f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:07.615878Z","signature_b64":"LtnWSb1zR5MFEk6welh2xmk+ApgIGjU3VHe3wm856KQ1RZ9A7TFXfHMZkORsEP0KocpMOGIBIDiCr270sua6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ae2666cd5af17202ae710ecbf1387983b6f2e5ea47a961710b0b8169363c7b0","last_reissued_at":"2026-05-27T01:05:07.614812Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:07.614812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Chen, Lei Zhang, Olivera Kotevska, Ravi K Madduri, Wenhan Wu, Zhishuai Guo","submitted_at":"2026-05-25T18:10:20Z","abstract_excerpt":"Graph neural networks (GNNs) achieve strong performance on relational data, but real-world graphs are often distributed across organizations that cannot share raw data due to privacy and policy constraints. Existing federated GNN methods either ignore cross-client links, leading to degraded accuracy, or require frequent embedding exchanges, incurring substantial communication and privacy costs. We propose CE-FedGNN, a communication-efficient and privacy-preserving federated GNN framework for learning over such coupled graphs. Our approach avoids sharing raw data or per-round embeddings by infr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26243","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/2605.26243/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":"2605.26243","created_at":"2026-05-27T01:05:07.614952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26243v1","created_at":"2026-05-27T01:05:07.614952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26243","created_at":"2026-05-27T01:05:07.614952+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLRGM3GVV4LS","created_at":"2026-05-27T01:05:07.614952+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLRGM3GVV4LSAKXH","created_at":"2026-05-27T01:05:07.614952+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLRGM3GV","created_at":"2026-05-27T01:05:07.614952+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/HLRGM3GVV4LSAKXHCDWL6E4HTA","json":"https://pith.science/pith/HLRGM3GVV4LSAKXHCDWL6E4HTA.json","graph_json":"https://pith.science/api/pith-number/HLRGM3GVV4LSAKXHCDWL6E4HTA/graph.json","events_json":"https://pith.science/api/pith-number/HLRGM3GVV4LSAKXHCDWL6E4HTA/events.json","paper":"https://pith.science/paper/HLRGM3GV"},"agent_actions":{"view_html":"https://pith.science/pith/HLRGM3GVV4LSAKXHCDWL6E4HTA","download_json":"https://pith.science/pith/HLRGM3GVV4LSAKXHCDWL6E4HTA.json","view_paper":"https://pith.science/paper/HLRGM3GV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26243&json=true","fetch_graph":"https://pith.science/api/pith-number/HLRGM3GVV4LSAKXHCDWL6E4HTA/graph.json","fetch_events":"https://pith.science/api/pith-number/HLRGM3GVV4LSAKXHCDWL6E4HTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLRGM3GVV4LSAKXHCDWL6E4HTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLRGM3GVV4LSAKXHCDWL6E4HTA/action/storage_attestation","attest_author":"https://pith.science/pith/HLRGM3GVV4LSAKXHCDWL6E4HTA/action/author_attestation","sign_citation":"https://pith.science/pith/HLRGM3GVV4LSAKXHCDWL6E4HTA/action/citation_signature","submit_replication":"https://pith.science/pith/HLRGM3GVV4LSAKXHCDWL6E4HTA/action/replication_record"}},"created_at":"2026-05-27T01:05:07.614952+00:00","updated_at":"2026-05-27T01:05:07.614952+00:00"}