{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KP24KX4EHZ6PS36HHDXOPLQUHF","short_pith_number":"pith:KP24KX4E","schema_version":"1.0","canonical_sha256":"53f5c55f843e7cf96fc738eee7ae14395e471ec5643b700532e3e34c6f4eaf83","source":{"kind":"arxiv","id":"2404.18848","version":3},"attestation_state":"computed","paper":{"title":"FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Qianqian Yang, Shunpu Tang, Yuxuan Yan, Zhiguo Shi","submitted_at":"2024-04-29T16:42:26Z","abstract_excerpt":"Despite their exceptional performance on various tasks after fine-tuning, pre-trained language models (PLMs) face significant challenges due to growing privacy concerns with data in centralized training methods. We consider federated learning (FL) to fine-tune PLMs in this paper. However, the substantial number of parameters in PLMs poses significant difficulties for client devices with limited communication and computational resources. One promising solution is to exploit parameter-efficient fine-tuning (PEFT) into FL, which trains a much smaller set of parameters than full parameter fine-tun"},"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":"2404.18848","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-29T16:42:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c598a0169bb9d49bc5e95f7ae115bd4ac0b66a683f14733aa95ba45cbb043e8e","abstract_canon_sha256":"40213f836eeb0a5b3065970dde541bd00f60c76317cbbd986b385c33b3b4438c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:21.729992Z","signature_b64":"cRJTpKdjRzI6cOQ+LzvFxeZAKjqoqWg/pRNauHEMx2p6WnJBr25srG0NRWR8ZZdcm8Bzfz5AORVIR+7otUHwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53f5c55f843e7cf96fc738eee7ae14395e471ec5643b700532e3e34c6f4eaf83","last_reissued_at":"2026-07-05T08:23:21.729510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:21.729510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Qianqian Yang, Shunpu Tang, Yuxuan Yan, Zhiguo Shi","submitted_at":"2024-04-29T16:42:26Z","abstract_excerpt":"Despite their exceptional performance on various tasks after fine-tuning, pre-trained language models (PLMs) face significant challenges due to growing privacy concerns with data in centralized training methods. We consider federated learning (FL) to fine-tune PLMs in this paper. However, the substantial number of parameters in PLMs poses significant difficulties for client devices with limited communication and computational resources. One promising solution is to exploit parameter-efficient fine-tuning (PEFT) into FL, which trains a much smaller set of parameters than full parameter fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18848","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/2404.18848/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":"2404.18848","created_at":"2026-07-05T08:23:21.729567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18848v3","created_at":"2026-07-05T08:23:21.729567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18848","created_at":"2026-07-05T08:23:21.729567+00:00"},{"alias_kind":"pith_short_12","alias_value":"KP24KX4EHZ6P","created_at":"2026-07-05T08:23:21.729567+00:00"},{"alias_kind":"pith_short_16","alias_value":"KP24KX4EHZ6PS36H","created_at":"2026-07-05T08:23:21.729567+00:00"},{"alias_kind":"pith_short_8","alias_value":"KP24KX4E","created_at":"2026-07-05T08:23:21.729567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12883","citing_title":"The Hidden Power of Scaling Factor in LoRA Optimization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29460","citing_title":"FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2501.06332","citing_title":"Aggregating Low Rank Adapters in Federated Fine-tuning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF","json":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF.json","graph_json":"https://pith.science/api/pith-number/KP24KX4EHZ6PS36HHDXOPLQUHF/graph.json","events_json":"https://pith.science/api/pith-number/KP24KX4EHZ6PS36HHDXOPLQUHF/events.json","paper":"https://pith.science/paper/KP24KX4E"},"agent_actions":{"view_html":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF","download_json":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF.json","view_paper":"https://pith.science/paper/KP24KX4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18848&json=true","fetch_graph":"https://pith.science/api/pith-number/KP24KX4EHZ6PS36HHDXOPLQUHF/graph.json","fetch_events":"https://pith.science/api/pith-number/KP24KX4EHZ6PS36HHDXOPLQUHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF/action/storage_attestation","attest_author":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF/action/author_attestation","sign_citation":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF/action/citation_signature","submit_replication":"https://pith.science/pith/KP24KX4EHZ6PS36HHDXOPLQUHF/action/replication_record"}},"created_at":"2026-07-05T08:23:21.729567+00:00","updated_at":"2026-07-05T08:23:21.729567+00:00"}