{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JC3BMPH4F7VKIOE6ECLJZ7M7X5","short_pith_number":"pith:JC3BMPH4","schema_version":"1.0","canonical_sha256":"48b6163cfc2feaa4389e20969cfd9fbf483a104e2bb38e2ddf1b6beb37e36200","source":{"kind":"arxiv","id":"2605.13475","version":1},"attestation_state":"computed","paper":{"title":"FedHPro: Federated Hyper-Prototype Learning via Gradient Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Hyper-prototypes aligned by gradient matching from client samples reduce semantic drift in federated prototype learning.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Wu, Guansong Pang, Haoran Li, Huan Wang, Jun Shen, Jun Yan, Ousman Manjang, Yanlong Zhai, Zhenyu Yang","submitted_at":"2026-05-13T13:01:17Z","abstract_excerpt":"Federated Learning (FL) enables collaborative training of distributed clients while protecting privacy. To enhance generalization capability in FL, prototype-based FL is in the spotlight, since shared global prototypes offer semantic anchors for aligning client-specific local prototypes. However, existing methods update global prototypes at the prototype-level via averaging local prototypes or refining global anchors, which often leads to semantic drift across clients and subsequently yields a misaligned global signal. To alleviate this issue, we introduce hyper-prototypes, defined by a set of"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13475","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:01:17Z","cross_cats_sorted":[],"title_canon_sha256":"9b20bcc00b31ee7d534a365f5943e681d1fe1ab3e2e3983be80dd4d006f482ae","abstract_canon_sha256":"e275fcd8e2594af598ec74a40670d98ccc5b857a4b42cd81479f0d2c576feed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:41.478493Z","signature_b64":"vLbrJ+1ew0nvIt2YAIkX9zMvpiYuPsWaad2l/t0SsH0q9kaiq3+oufNg3vqyjpIsPVjuwnVV3Pfaf9UqoikjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48b6163cfc2feaa4389e20969cfd9fbf483a104e2bb38e2ddf1b6beb37e36200","last_reissued_at":"2026-05-18T02:44:41.477777Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:41.477777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedHPro: Federated Hyper-Prototype Learning via Gradient Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Hyper-prototypes aligned by gradient matching from client samples reduce semantic drift in federated prototype learning.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Wu, Guansong Pang, Haoran Li, Huan Wang, Jun Shen, Jun Yan, Ousman Manjang, Yanlong Zhai, Zhenyu Yang","submitted_at":"2026-05-13T13:01:17Z","abstract_excerpt":"Federated Learning (FL) enables collaborative training of distributed clients while protecting privacy. To enhance generalization capability in FL, prototype-based FL is in the spotlight, since shared global prototypes offer semantic anchors for aligning client-specific local prototypes. However, existing methods update global prototypes at the prototype-level via averaging local prototypes or refining global anchors, which often leads to semantic drift across clients and subsequently yields a misaligned global signal. To alleviate this issue, we introduce hyper-prototypes, defined by a set of"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"hyper-prototypes produce a more semantically consistent global signal, and FedHPro achieves state-of-the-art performance on several benchmark datasets under diverse heterogeneous scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That matching gradients computed on real client samples will align hyper-prototypes more reliably than averaging local prototypes, without introducing new privacy leakage or optimization instability.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FedHPro introduces gradient-matched hyper-prototypes plus mutual-contrastive learning to produce semantically consistent global signals and reach state-of-the-art accuracy on heterogeneous image benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hyper-prototypes aligned by gradient matching from client samples reduce semantic drift in federated prototype learning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"73c7775217d26fde24604929157ff595b8e06f2484f2c39e73f1ef52fe8417fe"},"source":{"id":"2605.13475","kind":"arxiv","version":1},"verdict":{"id":"caa6e760-881e-4e95-a58d-e6bf01719f99","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:21:59.453163Z","strongest_claim":"hyper-prototypes produce a more semantically consistent global signal, and FedHPro achieves state-of-the-art performance on several benchmark datasets under diverse heterogeneous scenarios.","one_line_summary":"FedHPro introduces gradient-matched hyper-prototypes plus mutual-contrastive learning to produce semantically consistent global signals and reach state-of-the-art accuracy on heterogeneous image benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That matching gradients computed on real client samples will align hyper-prototypes more reliably than averaging local prototypes, without introducing new privacy leakage or optimization instability.","pith_extraction_headline":"Hyper-prototypes aligned by gradient matching from client samples reduce semantic drift in federated prototype learning."},"references":{"count":14,"sample":[{"doi":"","year":2066,"title":"Geodesic flow kernel for unsupervised domain adaptation","work_id":"30078da4-5702-4a95-b330-9b6301ace13e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2062,"title":"Learning support and trivial prototypes for interpretable image classification","work_id":"3f34da05-f0b7-4392-b5ea-30fb79842983","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"12 FedHPro: Federated Hyper-Prototype Learning via Gradient Matching A. Algorithm Pseudo-code Flow In this section, we describe the pseudo-code of our FedHPro in Algorithm 1: 1)Server-Side: we optimiz","work_id":"cb75084a-2f4e-4297-b7a1-619b6b206eaa","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"for the TinyImageNet dataset. The label skew heterogeneity level of clients is controlled by the standard deviation α of the Dirichlet distribution, and the quantity skew heterogeneity level is contro","work_id":"08a17d60-2f9c-40f2-84a3-f6a4f704bbef","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"is used for skin lesion classification and contains 8,912 training samples and 1,103 testing samples with 7 categories, and each sample’s size is scaled to224∗224 . Then, based on (Kaidi et al., 2019)","work_id":"240b0b88-c1f8-430d-9032-d066a7b7ebd2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":14,"snapshot_sha256":"a2362fba15b17627156b60fc7ae93c8e4c91c4648703dc75cb5d55c004a6c21b","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"543ef28dff658b3cec64dfa8e2d373a2576919cce2fc5e0ed023d3fed296c362"},"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":"2605.13475","created_at":"2026-05-18T02:44:41.477877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13475v1","created_at":"2026-05-18T02:44:41.477877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13475","created_at":"2026-05-18T02:44:41.477877+00:00"},{"alias_kind":"pith_short_12","alias_value":"JC3BMPH4F7VK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"JC3BMPH4F7VKIOE6","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"JC3BMPH4","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5","json":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5.json","graph_json":"https://pith.science/api/pith-number/JC3BMPH4F7VKIOE6ECLJZ7M7X5/graph.json","events_json":"https://pith.science/api/pith-number/JC3BMPH4F7VKIOE6ECLJZ7M7X5/events.json","paper":"https://pith.science/paper/JC3BMPH4"},"agent_actions":{"view_html":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5","download_json":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5.json","view_paper":"https://pith.science/paper/JC3BMPH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13475&json=true","fetch_graph":"https://pith.science/api/pith-number/JC3BMPH4F7VKIOE6ECLJZ7M7X5/graph.json","fetch_events":"https://pith.science/api/pith-number/JC3BMPH4F7VKIOE6ECLJZ7M7X5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5/action/storage_attestation","attest_author":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5/action/author_attestation","sign_citation":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5/action/citation_signature","submit_replication":"https://pith.science/pith/JC3BMPH4F7VKIOE6ECLJZ7M7X5/action/replication_record"}},"created_at":"2026-05-18T02:44:41.477877+00:00","updated_at":"2026-05-18T02:44:41.477877+00:00"}