{"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"}