{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NG3UI3Z227W5WNXYSRZG74XZUV","short_pith_number":"pith:NG3UI3Z2","schema_version":"1.0","canonical_sha256":"69b7446f3ad7eddb36f894726ff2f9a57857efc4afd552489878d086f055098d","source":{"kind":"arxiv","id":"2508.17431","version":4},"attestation_state":"computed","paper":{"title":"FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FedKLPR combines KL-divergence guidance with pruning and weighted aggregation to cut communication costs in federated person re-identification by 40-42 percent.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Po-Hsien Yu, Shao-Yi Chien, Yu-Syuan Tseng","submitted_at":"2025-08-24T16:11:41Z","abstract_excerpt":"Person re-identification (re-ID) is a fundamental task in intelligent surveillance and public safety. Federated learning (FL) provides a privacy-preserving paradigm for collaborative model training without centralized data collection. However, deploying FL in real-world re-ID systems remains challenging due to statistical heterogeneity caused by non-IID client data and the substantial communication overhead incurred by frequent transmission of large-scale models. To address these challenges, we propose FedKLPR, a lightweight and communication-efficient federated learning framework for person r"},"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":true},"canonical_record":{"source":{"id":"2508.17431","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T16:11:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4e8e665a2e60590032db14180426aed0fe796a3d8607deda0a47a1ea361e1ef3","abstract_canon_sha256":"c25644be4e8bcace613b0c9708d384be82b2475c65a7df5e9bef4d8914528848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:32.974973Z","signature_b64":"4vKT3vHzMJvCkXwpkcZC14asUjYIXOWh6Fz8LFnNvNYUlcEVegEi7k2F9oIsZgwyiDU53Ta5uoaN34mN8NkPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69b7446f3ad7eddb36f894726ff2f9a57857efc4afd552489878d086f055098d","last_reissued_at":"2026-05-20T00:05:32.974069Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:32.974069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FedKLPR combines KL-divergence guidance with pruning and weighted aggregation to cut communication costs in federated person re-identification by 40-42 percent.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Po-Hsien Yu, Shao-Yi Chien, Yu-Syuan Tseng","submitted_at":"2025-08-24T16:11:41Z","abstract_excerpt":"Person re-identification (re-ID) is a fundamental task in intelligent surveillance and public safety. Federated learning (FL) provides a privacy-preserving paradigm for collaborative model training without centralized data collection. However, deploying FL in real-world re-ID systems remains challenging due to statistical heterogeneity caused by non-IID client data and the substantial communication overhead incurred by frequent transmission of large-scale models. To address these challenges, we propose FedKLPR, a lightweight and communication-efficient federated learning framework for person r"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results on eight benchmark datasets demonstrate that FedKLPR achieves substantial communication savings while maintaining competitive accuracy. Compared with state-of-the-art methods, FedKLPR reduces communication cost by 40%--42% on ResNet-50 while achieving superior overall performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the combination of KL-Divergence Regularization Loss, KL-Divergence-aggregation Weight, Pruning-ratio-aggregation Weight, and Cross-Round Recovery will continue to preserve accuracy when pruning ratios and non-IID severity increase beyond the tested benchmark settings.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FedKLPR adds KL-regularized training, prune-weighted aggregation, and cross-round recovery to federated learning for re-ID, claiming 40-42% lower communication on ResNet-50 with competitive accuracy across eight datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FedKLPR combines KL-divergence guidance with pruning and weighted aggregation to cut communication costs in federated person re-identification by 40-42 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8157c1c08b7ff4ffe591a5b928bb47bd2127c06d6efb2d4a18064892a3defc79"},"source":{"id":"2508.17431","kind":"arxiv","version":4},"verdict":{"id":"30e7ea04-7e99-4dbc-b395-2e260638e93e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T20:53:59.950295Z","strongest_claim":"Experimental results on eight benchmark datasets demonstrate that FedKLPR achieves substantial communication savings while maintaining competitive accuracy. Compared with state-of-the-art methods, FedKLPR reduces communication cost by 40%--42% on ResNet-50 while achieving superior overall performance.","one_line_summary":"FedKLPR adds KL-regularized training, prune-weighted aggregation, and cross-round recovery to federated learning for re-ID, claiming 40-42% lower communication on ResNet-50 with competitive accuracy across eight datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the combination of KL-Divergence Regularization Loss, KL-Divergence-aggregation Weight, Pruning-ratio-aggregation Weight, and Cross-Round Recovery will continue to preserve accuracy when pruning ratios and non-IID severity increase beyond the tested benchmark settings.","pith_extraction_headline":"FedKLPR combines KL-divergence guidance with pruning and weighted aggregation to cut communication costs in federated person re-identification by 40-42 percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.17431/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":1,"snapshot_sha256":"23f56e2bf9f43f58b2d8359c610f825f8abbbad3021be823f519303b0080c328"},"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":"2508.17431","created_at":"2026-05-20T00:05:32.974218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17431v4","created_at":"2026-05-20T00:05:32.974218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17431","created_at":"2026-05-20T00:05:32.974218+00:00"},{"alias_kind":"pith_short_12","alias_value":"NG3UI3Z227W5","created_at":"2026-05-20T00:05:32.974218+00:00"},{"alias_kind":"pith_short_16","alias_value":"NG3UI3Z227W5WNXY","created_at":"2026-05-20T00:05:32.974218+00:00"},{"alias_kind":"pith_short_8","alias_value":"NG3UI3Z2","created_at":"2026-05-20T00:05:32.974218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV","json":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV.json","graph_json":"https://pith.science/api/pith-number/NG3UI3Z227W5WNXYSRZG74XZUV/graph.json","events_json":"https://pith.science/api/pith-number/NG3UI3Z227W5WNXYSRZG74XZUV/events.json","paper":"https://pith.science/paper/NG3UI3Z2"},"agent_actions":{"view_html":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV","download_json":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV.json","view_paper":"https://pith.science/paper/NG3UI3Z2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17431&json=true","fetch_graph":"https://pith.science/api/pith-number/NG3UI3Z227W5WNXYSRZG74XZUV/graph.json","fetch_events":"https://pith.science/api/pith-number/NG3UI3Z227W5WNXYSRZG74XZUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV/action/storage_attestation","attest_author":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV/action/author_attestation","sign_citation":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV/action/citation_signature","submit_replication":"https://pith.science/pith/NG3UI3Z227W5WNXYSRZG74XZUV/action/replication_record"}},"created_at":"2026-05-20T00:05:32.974218+00:00","updated_at":"2026-05-20T00:05:32.974218+00:00"}