{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:25PPMTNJFPJWKBH3FHRBYDX6OJ","short_pith_number":"pith:25PPMTNJ","schema_version":"1.0","canonical_sha256":"d75ef64da92bd36504fb29e21c0efe727d27d7482ef5d42f93db7d7336fce8bd","source":{"kind":"arxiv","id":"2402.06974","version":3},"attestation_state":"computed","paper":{"title":"Hypernetwork-Driven Model Fusion for Federated Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ami Beuret, Joachim M. Buhmann, Marc Bartholet, Se-Young Yun, Taehyeon Kim","submitted_at":"2024-02-10T15:42:03Z","abstract_excerpt":"Federated Learning (FL) faces significant challenges with domain shifts in heterogeneous data, degrading performance. Traditional domain generalization aims to learn domain-invariant features, but the federated nature of model averaging often limits this due to its linear aggregation of local learning. To address this, we propose a robust framework, coined as hypernetwork-based Federated Fusion (hFedF), using hypernetworks for non-linear aggregation, facilitating generalization to unseen domains. Our method employs client-specific embeddings and gradient alignment techniques to manage domain g"},"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":"2402.06974","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T15:42:03Z","cross_cats_sorted":[],"title_canon_sha256":"b3835ff32893cb5251d5eff8c28f22d9253fc185de658689336ec0ea636058f6","abstract_canon_sha256":"6febdacc9ebbae92253b0ba7154a2347d60c45c69bc1f9ddf35ce731fa7e0e0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:01.360155Z","signature_b64":"dOKmuPAlETp9IXLQwi1XoVt2+UdfegFCIzmbagsQ1prsc1qiFph9I+6KgNvv1uv9xjwYPiFqe5JgygzCk7olCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d75ef64da92bd36504fb29e21c0efe727d27d7482ef5d42f93db7d7336fce8bd","last_reissued_at":"2026-07-05T08:24:01.359656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:01.359656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypernetwork-Driven Model Fusion for Federated Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ami Beuret, Joachim M. Buhmann, Marc Bartholet, Se-Young Yun, Taehyeon Kim","submitted_at":"2024-02-10T15:42:03Z","abstract_excerpt":"Federated Learning (FL) faces significant challenges with domain shifts in heterogeneous data, degrading performance. Traditional domain generalization aims to learn domain-invariant features, but the federated nature of model averaging often limits this due to its linear aggregation of local learning. To address this, we propose a robust framework, coined as hypernetwork-based Federated Fusion (hFedF), using hypernetworks for non-linear aggregation, facilitating generalization to unseen domains. Our method employs client-specific embeddings and gradient alignment techniques to manage domain g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06974","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/2402.06974/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":"2402.06974","created_at":"2026-07-05T08:24:01.359717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06974v3","created_at":"2026-07-05T08:24:01.359717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06974","created_at":"2026-07-05T08:24:01.359717+00:00"},{"alias_kind":"pith_short_12","alias_value":"25PPMTNJFPJW","created_at":"2026-07-05T08:24:01.359717+00:00"},{"alias_kind":"pith_short_16","alias_value":"25PPMTNJFPJWKBH3","created_at":"2026-07-05T08:24:01.359717+00:00"},{"alias_kind":"pith_short_8","alias_value":"25PPMTNJ","created_at":"2026-07-05T08:24:01.359717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.05148","citing_title":"LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ","json":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ.json","graph_json":"https://pith.science/api/pith-number/25PPMTNJFPJWKBH3FHRBYDX6OJ/graph.json","events_json":"https://pith.science/api/pith-number/25PPMTNJFPJWKBH3FHRBYDX6OJ/events.json","paper":"https://pith.science/paper/25PPMTNJ"},"agent_actions":{"view_html":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ","download_json":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ.json","view_paper":"https://pith.science/paper/25PPMTNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06974&json=true","fetch_graph":"https://pith.science/api/pith-number/25PPMTNJFPJWKBH3FHRBYDX6OJ/graph.json","fetch_events":"https://pith.science/api/pith-number/25PPMTNJFPJWKBH3FHRBYDX6OJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ/action/storage_attestation","attest_author":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ/action/author_attestation","sign_citation":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ/action/citation_signature","submit_replication":"https://pith.science/pith/25PPMTNJFPJWKBH3FHRBYDX6OJ/action/replication_record"}},"created_at":"2026-07-05T08:24:01.359717+00:00","updated_at":"2026-07-05T08:24:01.359717+00:00"}