{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FKNCJUBEMNVGRP7SOQGKHXMD47","short_pith_number":"pith:FKNCJUBE","schema_version":"1.0","canonical_sha256":"2a9a24d024636a68bff2740ca3dd83e7c0c612676723e26b9df7de71d074b46e","source":{"kind":"arxiv","id":"2311.13250","version":2},"attestation_state":"computed","paper":{"title":"FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongtao Lu, Shalayiding Sirejiding, Suizhi Huang, Yue Ding, Yuwen Yang, Yuxiang Lu","submitted_at":"2023-11-22T09:12:50Z","abstract_excerpt":"Federated Learning (FL) enables joint training across distributed clients using their local data privately. Federated Multi-Task Learning (FMTL) builds on FL to handle multiple tasks, assuming model congruity that identical model architecture is deployed in each client. To relax this assumption and thus extend real-world applicability, we introduce a novel problem setting, Hetero-Client Federated Multi-Task Learning (HC-FMTL), to accommodate diverse task setups. The main challenge of HC-FMTL is the model incongruity issue that invalidates conventional aggregation methods. It also escalates the"},"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":"2311.13250","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T09:12:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f4d117cd9a1be99adf217e8e0051ddd8f3ee5800d40f5f3f59fde69ed668fa56","abstract_canon_sha256":"ed5f872ec8ecaeb70764c4f562f802e0071113d18de32db7b80ab8791c0c7f15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:21.668880Z","signature_b64":"RcQHMg1uo3Cf5BDgY1LnYXFpOB0i8CKnOSXgxAc8LD9jym4KAtK5smYuNjUD88L+h0NwxriOW2C/VGceTAmaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a9a24d024636a68bff2740ca3dd83e7c0c612676723e26b9df7de71d074b46e","last_reissued_at":"2026-07-05T07:50:21.668381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:21.668381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongtao Lu, Shalayiding Sirejiding, Suizhi Huang, Yue Ding, Yuwen Yang, Yuxiang Lu","submitted_at":"2023-11-22T09:12:50Z","abstract_excerpt":"Federated Learning (FL) enables joint training across distributed clients using their local data privately. Federated Multi-Task Learning (FMTL) builds on FL to handle multiple tasks, assuming model congruity that identical model architecture is deployed in each client. To relax this assumption and thus extend real-world applicability, we introduce a novel problem setting, Hetero-Client Federated Multi-Task Learning (HC-FMTL), to accommodate diverse task setups. The main challenge of HC-FMTL is the model incongruity issue that invalidates conventional aggregation methods. It also escalates the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13250","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/2311.13250/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":"2311.13250","created_at":"2026-07-05T07:50:21.668443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13250v2","created_at":"2026-07-05T07:50:21.668443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13250","created_at":"2026-07-05T07:50:21.668443+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKNCJUBEMNVG","created_at":"2026-07-05T07:50:21.668443+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKNCJUBEMNVGRP7S","created_at":"2026-07-05T07:50:21.668443+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKNCJUBE","created_at":"2026-07-05T07:50:21.668443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06376","citing_title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47","json":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47.json","graph_json":"https://pith.science/api/pith-number/FKNCJUBEMNVGRP7SOQGKHXMD47/graph.json","events_json":"https://pith.science/api/pith-number/FKNCJUBEMNVGRP7SOQGKHXMD47/events.json","paper":"https://pith.science/paper/FKNCJUBE"},"agent_actions":{"view_html":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47","download_json":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47.json","view_paper":"https://pith.science/paper/FKNCJUBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13250&json=true","fetch_graph":"https://pith.science/api/pith-number/FKNCJUBEMNVGRP7SOQGKHXMD47/graph.json","fetch_events":"https://pith.science/api/pith-number/FKNCJUBEMNVGRP7SOQGKHXMD47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47/action/storage_attestation","attest_author":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47/action/author_attestation","sign_citation":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47/action/citation_signature","submit_replication":"https://pith.science/pith/FKNCJUBEMNVGRP7SOQGKHXMD47/action/replication_record"}},"created_at":"2026-07-05T07:50:21.668443+00:00","updated_at":"2026-07-05T07:50:21.668443+00:00"}