{"total":12,"items":[{"citing_arxiv_id":"2607.00173","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TallyTrain: Communication-Efficient Federated Distillation","primary_cat":"cs.LG","submitted_at":"2026-06-30T20:47:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TallyTrain is a hard-label distillation protocol for federated learning that uses argmax transmission and optional sparse merges to match soft-label performance at up to 1000x lower communication cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08252","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Quantifying and Defending against the Privacy Risk in Logit-based Federated Learning","primary_cat":"cs.CR","submitted_at":"2026-06-06T16:40:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Logit-based federated learning leaks private model information to a semi-honest server via shared logits even with unrelated public data, enabling an adaptive stealing attack with theoretical bounds and a logit-perturbation defense.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21322","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:50:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedKDNAS combines client-side neural architecture search with knowledge distillation from aggregated server predictions to improve accuracy and efficiency in heterogeneous federated learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14886","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring","primary_cat":"cs.AI","submitted_at":"2026-05-14T14:31:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09356","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Function-Space ADMM for Decentralized Federated Learning: A Control Theoretic Perspective","primary_cat":"cs.LG","submitted_at":"2026-05-10T06:11:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FedF-ADMM uses function-space ADMM updates projected via knowledge distillation plus a PI-like stabilization term to deliver faster, more stable convergence and higher accuracy than prior decentralized FL methods under severe non-IID conditions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"was proposed for data-center environments [22], [23], where devices train local models and exchange shared output pre- dictions, which are averaged to form soft labels. This process can be viewed as a distributed form of KD [24]. While co- distillation was designed for data-center environments, and thus it assumes shared training data, the similar idea has been proposed for FL scenarios. Jeonget al.[25] proposed KD-based FL known as feder- ated distillation (FD) and federated augmentation (FAug) to address non-IID issues by generating missing samples using generative models, and later extended these schemes for multi- hop DFL in [26]. Itaharaet al.[27] proposed a KD-based semi-supervised FL algorithm to enhance robustness against malicious clients."},{"citing_arxiv_id":"2605.05959","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning","primary_cat":"cs.AI","submitted_at":"2026-05-07T10:06:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FedSAF shifts prototype alignment in heterogeneous federated learning from coordinate matching to inter-class structural relations and reports up to 3.52% gains over prior methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25018","ref_index":254,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Internet of Everything in the 6G Era: Paradigms, Enablers, Potentials and Future Directions","primary_cat":"cs.ET","submitted_at":"2026-04-27T21:40:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"The paper provides a structured overview of IoE concepts, components, architectures, enabling technologies, challenges, and open research directions for 6G-enabled IoE systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12160","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PubSwap: Public-Data Off-Policy Coordination for Federated RLVR","primary_cat":"cs.LG","submitted_at":"2026-04-14T00:35:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"This is stronger than requiring Lipschitzness in the optimization variable alone with a fixed sampling policy, which is sufficient for our case, as it additionally requires that the expected GRPO gradient varies smoothly as the response distribution shifts with the policy. Now using assumption 1 we have gpriv B (θ)−g priv B (θ′) ≤L priv∥θ−θ ′∥. (7) and using equations 7 and 6 θ(t+1) n −θ (t+1) n′ ≤(1+ηL priv) θ(t) n −θ (t) n′ +ηH (t) n,n′ +η \u0010 ξ(t) n + ξ(t) n′ \u0011 , where H(t) n,n′ := gpriv B(t) n (θ(t) n′ )−g priv B(t) n′ (θ(t) n′ ) . Further define the population private gradient to quantify the noise from minibatch selection gpriv n (θ):=E Bn h gpriv Bn (θ)"},{"citing_arxiv_id":"2508.14769","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data","primary_cat":"cs.LG","submitted_at":"2025-08-20T15:17:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"EdgeFD uses a KMeans-based client-side filter to improve federated distillation accuracy close to IID levels on non-IID data distributions for resource-constrained edge devices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.13543","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning","primary_cat":"cs.LG","submitted_at":"2025-03-16T04:35:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FedTSP builds class prototypes from LLM-generated text descriptions via PLMs and trainable prompts to preserve semantic relationships and reduce heterogeneity effects in federated learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2406.10861","ref_index":61,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","primary_cat":"cs.LG","submitted_at":"2024-06-16T09:12:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A survey organizing knowledge distillation techniques for addressing privacy, heterogeneity, communication, and personalization challenges in federated learning.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"preprint arXiv:1811.11479 (2018). J. ACM, Vol. 37, No. 4, Article 111. Publication date: August 2024. 111:30 L. Qin, et al. [60] Hai Jin, Dongshan Bai, Dezhong Yao, Yutong Dai, Lin Gu, Chen Yu, and Lichao Sun. 2022. Personalized edge intelligence via federated self-knowledge distillation. IEEE Transactions on Parallel and Distributed Systems 34, 2 (2022), 567-580. [61] Changxing Jing, Yan Huang, Yihong Zhuang, Liyan Sun, Zhenlong Xiao, Yue Huang, and Xinghao Ding. 2023. Exploring personalization via federated representation Learning on non-IID data. Neural Networks 163 (2023), 354-366. [62] Attila Kádár and Dániel Hadházi. 2022. FedLinked: A client-wise distilled representation based semi-supervised collaborative multitask learning scheme."},{"citing_arxiv_id":"1907.06426","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-hop Federated Private Data Augmentation with Sample Compression","primary_cat":"cs.LG","submitted_at":"2019-07-15T10:54:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"MultFAug combines multi-hop relaying and sample compression in federated settings to enhance privacy guarantees, cut transmission delay, and raise local training performance on non-IID data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}