{"paper":{"title":"BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"BiFedKD uses bidirectional knowledge distillation with temperature-scaled aggregation to align ECG clients under non-IID and long-tailed label distributions while cutting communication and computation costs.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hen-Wei Huang, Tiancheng Cao, Zixuan Shu","submitted_at":"2026-05-14T14:31:02Z","abstract_excerpt":"Electrocardiogram (ECG) monitoring in Internet of Medical Things (IoMT) networks is constrained by strict data-sharing regulations and privacy concerns. Federated learning (FL) enables collaborative learning by keeping raw ECG data on devices, but frequent transmissions of high-dimensional model updates incur heavy per-round traffic over bandwidth-limited links. To alleviate this bottleneck, federated distillation (FD) replaces parameter exchange with logit-based knowledge transfer. However, the performance of FD often degrades under the non-independent and identically distributed (non-IID) an"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on the MIT-BIH Arrhythmia dataset show that BiFedKD improves accuracy and Macro-F1 over the baseline by 3.52% and 9.93%, respectively. Moreover, to reach the same Macro-F1, BiFedKD reduces communication overhead by 40% and computation cost by 71.7% compared with the baseline.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the aggregation-by-distillation pipeline with temperature scaling produces a stable global distillation signal sufficient to align clients under non-IID and long-tailed ECG label distributions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"BiFedKD improves ECG classification accuracy by 3.52% and Macro-F1 by 9.93% on MIT-BIH while cutting communication overhead 40% and computation cost 71.7% versus baseline federated methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"BiFedKD uses bidirectional knowledge distillation with temperature-scaled aggregation to align ECG clients under non-IID and long-tailed label distributions while cutting communication and computation costs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cd26bd06e90114b159981856324dc7497e748cba7d6574f0b2fc19be6252e1c5"},"source":{"id":"2605.14886","kind":"arxiv","version":1},"verdict":{"id":"a6d72dfe-ad63-450c-bc94-325aafffc3a2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:08:51.674758Z","strongest_claim":"Experiments on the MIT-BIH Arrhythmia dataset show that BiFedKD improves accuracy and Macro-F1 over the baseline by 3.52% and 9.93%, respectively. Moreover, to reach the same Macro-F1, BiFedKD reduces communication overhead by 40% and computation cost by 71.7% compared with the baseline.","one_line_summary":"BiFedKD improves ECG classification accuracy by 3.52% and Macro-F1 by 9.93% on MIT-BIH while cutting communication overhead 40% and computation cost 71.7% versus baseline federated methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the aggregation-by-distillation pipeline with temperature scaling produces a stable global distillation signal sufficient to align clients under non-IID and long-tailed ECG label distributions.","pith_extraction_headline":"BiFedKD uses bidirectional knowledge distillation with temperature-scaled aggregation to align ECG clients under non-IID and long-tailed label distributions while cutting communication and computation costs."},"references":{"count":15,"sample":[{"doi":"10.1016/j.neucom.2023.126719","year":2023,"title":"Internet of medical things: A systematic review,","work_id":"725cdc8f-5f30-4aae-bc40-fca4690e1975","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Federated machine learning: Concept and applications,","work_id":"f1bf781e-a004-45ea-81ea-407321ef68a3","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Federated learning for privacy preservation in smart healthcare systems: A comprehensive survey,","work_id":"6baec9da-e745-4fc1-8813-1f5cf420788c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Fedsl: Federated split learning for collaborative healthcare analytics on resource-constrained wearable iomt devices,","work_id":"8d82c0f4-4749-4050-9d5f-cc84c98a5b6b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Distilling the Knowledge in a Neural Network","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","ref_index":5,"cited_arxiv_id":"1503.02531","is_internal_anchor":true}],"resolved_work":15,"snapshot_sha256":"d86533607295f52e3b4c50280e5453a7eb3163db676ff060bcc77875e534a522","internal_anchors":1},"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"}