{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WNQW2XNXYEY5MWED4IO2D7YI4U","short_pith_number":"pith:WNQW2XNX","schema_version":"1.0","canonical_sha256":"b3616d5db7c131d65883e21da1ff08e51fc7d1e2f2a8291ebc9aa65ebbe27bf3","source":{"kind":"arxiv","id":"2405.14791","version":2},"attestation_state":"computed","paper":{"title":"Recurrent Early Exits for Federated Learning with Heterogeneous Clients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Da Li, Ferenc Husz\\'ar, Javier Fernandez-Marques, {\\L}ukasz Dudziak, Nicholas D. Lane, Royson Lee, Shell Xu Hu, Stefanos Laskaridis, Timothy Hospedales","submitted_at":"2024-05-23T17:01:53Z","abstract_excerpt":"Federated learning (FL) has enabled distributed learning of a model across multiple clients in a privacy-preserving manner. One of the main challenges of FL is to accommodate clients with varying hardware capacities; clients have differing compute and memory requirements. To tackle this challenge, recent state-of-the-art approaches leverage the use of early exits. Nonetheless, these approaches fall short of mitigating the challenges of joint learning multiple exit classifiers, often relying on hand-picked heuristic solutions for knowledge distillation among classifiers and/or utilizing additio"},"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":"2405.14791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T17:01:53Z","cross_cats_sorted":["cs.CV","cs.DC"],"title_canon_sha256":"fbb5030493c62c9fc149f046de422356c54091ad455561339a1ae4319287e602","abstract_canon_sha256":"715a84157989fd41891e694b59da23433b4b1411adf752c084149cd9ffbbbe00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:24.281304Z","signature_b64":"gq7aL7Bo6ykVctSdMVZSUjjGhkXEqlLvspbMOnNKByW001wHZgeualRFQqd/6MkbtyQ27qbSDy6W6gv+hwEtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3616d5db7c131d65883e21da1ff08e51fc7d1e2f2a8291ebc9aa65ebbe27bf3","last_reissued_at":"2026-07-05T08:23:24.280860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:24.280860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Early Exits for Federated Learning with Heterogeneous Clients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Da Li, Ferenc Husz\\'ar, Javier Fernandez-Marques, {\\L}ukasz Dudziak, Nicholas D. Lane, Royson Lee, Shell Xu Hu, Stefanos Laskaridis, Timothy Hospedales","submitted_at":"2024-05-23T17:01:53Z","abstract_excerpt":"Federated learning (FL) has enabled distributed learning of a model across multiple clients in a privacy-preserving manner. One of the main challenges of FL is to accommodate clients with varying hardware capacities; clients have differing compute and memory requirements. To tackle this challenge, recent state-of-the-art approaches leverage the use of early exits. Nonetheless, these approaches fall short of mitigating the challenges of joint learning multiple exit classifiers, often relying on hand-picked heuristic solutions for knowledge distillation among classifiers and/or utilizing additio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14791","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/2405.14791/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":"2405.14791","created_at":"2026-07-05T08:23:24.280915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14791v2","created_at":"2026-07-05T08:23:24.280915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14791","created_at":"2026-07-05T08:23:24.280915+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNQW2XNXYEY5","created_at":"2026-07-05T08:23:24.280915+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNQW2XNXYEY5MWED","created_at":"2026-07-05T08:23:24.280915+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNQW2XNX","created_at":"2026-07-05T08:23:24.280915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.23070","citing_title":"FLEX-MoE: Federated Mixture-of-Experts with Load-balanced Expert Assignment for Edge Computing","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U","json":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U.json","graph_json":"https://pith.science/api/pith-number/WNQW2XNXYEY5MWED4IO2D7YI4U/graph.json","events_json":"https://pith.science/api/pith-number/WNQW2XNXYEY5MWED4IO2D7YI4U/events.json","paper":"https://pith.science/paper/WNQW2XNX"},"agent_actions":{"view_html":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U","download_json":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U.json","view_paper":"https://pith.science/paper/WNQW2XNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14791&json=true","fetch_graph":"https://pith.science/api/pith-number/WNQW2XNXYEY5MWED4IO2D7YI4U/graph.json","fetch_events":"https://pith.science/api/pith-number/WNQW2XNXYEY5MWED4IO2D7YI4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U/action/storage_attestation","attest_author":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U/action/author_attestation","sign_citation":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U/action/citation_signature","submit_replication":"https://pith.science/pith/WNQW2XNXYEY5MWED4IO2D7YI4U/action/replication_record"}},"created_at":"2026-07-05T08:23:24.280915+00:00","updated_at":"2026-07-05T08:23:24.280915+00:00"}