{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W26GQWBQLKUD72E3BYQUS6N7PU","short_pith_number":"pith:W26GQWBQ","schema_version":"1.0","canonical_sha256":"b6bc6858305aa83fe89b0e214979bf7d0e75083b6308ce8d6175e5dbbf38b180","source":{"kind":"arxiv","id":"2404.14061","version":2},"attestation_state":"computed","paper":{"title":"FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.SI"],"primary_cat":"cs.LG","authors_text":"Di Wu, Miao Hu, Rong-Hua Li, Xunkai Li, Yinlin Zhu, Zhengyu Wu","submitted_at":"2024-04-22T10:19:02Z","abstract_excerpt":"Subgraph federated learning (subgraph-FL) is a new distributed paradigm that facilitates the collaborative training of graph neural networks (GNNs) by multi-client subgraphs. Unfortunately, a significant challenge of subgraph-FL arises from subgraph heterogeneity, which stems from node and topology variation, causing the impaired performance of the global GNN. Despite various studies, they have not yet thoroughly investigated the impact mechanism of subgraph heterogeneity. To this end, we decouple node and topology variation, revealing that they correspond to differences in label distribution "},"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":"2404.14061","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-22T10:19:02Z","cross_cats_sorted":["cs.AI","cs.DB","cs.SI"],"title_canon_sha256":"6fa7adef722b01a044be44fad02d8a2945b919a7d3f28906fe664c26d068e590","abstract_canon_sha256":"862f5b6a8c8ff7c42b5ca0361e30e962b785fbf445f111ef229d70749050d11e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:59.605606Z","signature_b64":"LjZRgSNlMAaKFK2RxzFeef26CgjX1cpHZyEnKtdS8ygr4jfUCd1ZrwAbu0cBT+FfNZrPXDuSDjaXQzzg3220CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6bc6858305aa83fe89b0e214979bf7d0e75083b6308ce8d6175e5dbbf38b180","last_reissued_at":"2026-07-05T08:11:59.605071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:59.605071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.SI"],"primary_cat":"cs.LG","authors_text":"Di Wu, Miao Hu, Rong-Hua Li, Xunkai Li, Yinlin Zhu, Zhengyu Wu","submitted_at":"2024-04-22T10:19:02Z","abstract_excerpt":"Subgraph federated learning (subgraph-FL) is a new distributed paradigm that facilitates the collaborative training of graph neural networks (GNNs) by multi-client subgraphs. Unfortunately, a significant challenge of subgraph-FL arises from subgraph heterogeneity, which stems from node and topology variation, causing the impaired performance of the global GNN. Despite various studies, they have not yet thoroughly investigated the impact mechanism of subgraph heterogeneity. To this end, we decouple node and topology variation, revealing that they correspond to differences in label distribution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14061","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/2404.14061/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":"2404.14061","created_at":"2026-07-05T08:11:59.605130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14061v2","created_at":"2026-07-05T08:11:59.605130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14061","created_at":"2026-07-05T08:11:59.605130+00:00"},{"alias_kind":"pith_short_12","alias_value":"W26GQWBQLKUD","created_at":"2026-07-05T08:11:59.605130+00:00"},{"alias_kind":"pith_short_16","alias_value":"W26GQWBQLKUD72E3","created_at":"2026-07-05T08:11:59.605130+00:00"},{"alias_kind":"pith_short_8","alias_value":"W26GQWBQ","created_at":"2026-07-05T08:11:59.605130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20382","citing_title":"Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approach","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11919","citing_title":"STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU","json":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU.json","graph_json":"https://pith.science/api/pith-number/W26GQWBQLKUD72E3BYQUS6N7PU/graph.json","events_json":"https://pith.science/api/pith-number/W26GQWBQLKUD72E3BYQUS6N7PU/events.json","paper":"https://pith.science/paper/W26GQWBQ"},"agent_actions":{"view_html":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU","download_json":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU.json","view_paper":"https://pith.science/paper/W26GQWBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14061&json=true","fetch_graph":"https://pith.science/api/pith-number/W26GQWBQLKUD72E3BYQUS6N7PU/graph.json","fetch_events":"https://pith.science/api/pith-number/W26GQWBQLKUD72E3BYQUS6N7PU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU/action/storage_attestation","attest_author":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU/action/author_attestation","sign_citation":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU/action/citation_signature","submit_replication":"https://pith.science/pith/W26GQWBQLKUD72E3BYQUS6N7PU/action/replication_record"}},"created_at":"2026-07-05T08:11:59.605130+00:00","updated_at":"2026-07-05T08:11:59.605130+00:00"}