{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5ZHTU55MKQ66SXGGLH3YAMM63O","short_pith_number":"pith:5ZHTU55M","schema_version":"1.0","canonical_sha256":"ee4f3a77ac543de95cc659f780319edb80dd3e88194a232a01eb30921b2f29d8","source":{"kind":"arxiv","id":"2101.11296","version":3},"attestation_state":"computed","paper":{"title":"FedH2L: Federated Learning with Model and Statistical Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haibo Mi, Huaimin Wang, Timothy M. Hospedales, Wei Zhou, Yiying Li","submitted_at":"2021-01-27T10:10:18Z","abstract_excerpt":"Federated learning (FL) enables distributed participants to collectively learn a strong global model without sacrificing their individual data privacy. Mainstream FL approaches require each participant to share a common network architecture and further assume that data are are sampled IID across participants. However, in real-world deployments participants may require heterogeneous network architectures; and the data distribution is almost certainly non-uniform across participants. To address these issues we introduce FedH2L, which is agnostic to both the model architecture and robust to diffe"},"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":"2101.11296","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T10:10:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ddf38d91d53b03c03f9f3cb1c857df9df5aea21d63d7829736ed7c4448a66ca4","abstract_canon_sha256":"ec83ec3e6eca8fd7e182a3ea86a2ec7d13c1d7629625e83adbd2d31b6095157a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:49.972281Z","signature_b64":"dh8JiIyA8gWwnJesS2Mmc2VV8wviBujFYBFyyEUiu3+V+133eCWKBINOaciInv2se67suvR+Sv1Lt5plpSm3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee4f3a77ac543de95cc659f780319edb80dd3e88194a232a01eb30921b2f29d8","last_reissued_at":"2026-07-05T03:00:49.971768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:49.971768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedH2L: Federated Learning with Model and Statistical Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haibo Mi, Huaimin Wang, Timothy M. Hospedales, Wei Zhou, Yiying Li","submitted_at":"2021-01-27T10:10:18Z","abstract_excerpt":"Federated learning (FL) enables distributed participants to collectively learn a strong global model without sacrificing their individual data privacy. Mainstream FL approaches require each participant to share a common network architecture and further assume that data are are sampled IID across participants. However, in real-world deployments participants may require heterogeneous network architectures; and the data distribution is almost certainly non-uniform across participants. To address these issues we introduce FedH2L, which is agnostic to both the model architecture and robust to diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11296","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/2101.11296/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":"2101.11296","created_at":"2026-07-05T03:00:49.971830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.11296v3","created_at":"2026-07-05T03:00:49.971830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11296","created_at":"2026-07-05T03:00:49.971830+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZHTU55MKQ66","created_at":"2026-07-05T03:00:49.971830+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZHTU55MKQ66SXGG","created_at":"2026-07-05T03:00:49.971830+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZHTU55M","created_at":"2026-07-05T03:00:49.971830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30615","citing_title":"Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage","ref_index":152,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O","json":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O.json","graph_json":"https://pith.science/api/pith-number/5ZHTU55MKQ66SXGGLH3YAMM63O/graph.json","events_json":"https://pith.science/api/pith-number/5ZHTU55MKQ66SXGGLH3YAMM63O/events.json","paper":"https://pith.science/paper/5ZHTU55M"},"agent_actions":{"view_html":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O","download_json":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O.json","view_paper":"https://pith.science/paper/5ZHTU55M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.11296&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZHTU55MKQ66SXGGLH3YAMM63O/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZHTU55MKQ66SXGGLH3YAMM63O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O/action/storage_attestation","attest_author":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O/action/author_attestation","sign_citation":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O/action/citation_signature","submit_replication":"https://pith.science/pith/5ZHTU55MKQ66SXGGLH3YAMM63O/action/replication_record"}},"created_at":"2026-07-05T03:00:49.971830+00:00","updated_at":"2026-07-05T03:00:49.971830+00:00"}