{"total":33,"items":[{"citing_arxiv_id":"2606.29322","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning","primary_cat":"cs.LG","submitted_at":"2026-06-28T10:28:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SP-CACW is a convergence-aware client weighting scheme for selfish personalized federated learning that minimizes an upper bound on the target client's convergence error and can zero out harmful peers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30892","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Bandwidth Allocation with Device Partitioning for Federated Learning over Industrial IoT networks","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:27:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A device-partitioning bandwidth allocation policy for federated learning over IIoT networks that provably reduces total training time compared to any non-partitioning scheme.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00134","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"XAI-SOH-FL: Enhancing SOH-FL with Adaptive Aggregation and Explainable AI for Intrusion Detection in Heterogeneous IoT","primary_cat":"cs.CR","submitted_at":"2026-05-28T21:23:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"XAI-SOH-FL extends SOH-FL with adaptive gamma via Bayesian optimization and SHAP interpretability, reporting 94.12% accuracy and 0.92 F1 on CICIDS2017 while converging faster than baseline.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28347","ref_index":66,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models","primary_cat":"cs.AI","submitted_at":"2026-05-27T11:51:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedMPT applies causal modeling and LLM-driven condition prompts with optimal transport and gating to perform federated multi-label prompt tuning of VLMs, claiming competitive results on benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22898","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-05-21T16:06:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FIRMA introduces Fibonacci ring aggregation protocols for server-free federated learning that maintain private heads and achieve higher accuracy than FedAvg under label skew across multiple benchmarks and heterogeneity regimes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20975","ref_index":36,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-05-20T10:00:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Proactive client selection in federated learning via differentially private mutual information and simulated annealing to optimize Potential Federation Loss for utility and fairness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20866","ref_index":62,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging","primary_cat":"cs.LG","submitted_at":"2026-05-20T08:01:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Hmax−1X t=0 E \u0002 ∇f(¯xr), ¯∇r t {xr i }n i=1 \u0003 .(60) Further, ∇f(¯xr), ¯∇r t (55) = 1 n X i∈At ∇f(¯xr),∇f(w r i,t) .(61) Using the inequality ⟨a, b⟩ ≥ 1 2 ∥a∥2 − 1 2 ∥a−b∥ 2, with a=∇f(¯x r), b=∇f(w r i,t), and then using L-Lipschitz continuity of ∇f (cf. Assumption 2.3), we obtain ∇f(¯xr),∇f(w r i,t) ≥ 1 2 ∥∇f(¯xr)∥2 − L2 2 ∥wr i,t −¯xr∥2.(62) Plugging (62) into (61), and usingm t =|A t|, we get ∇f(¯xr), ¯∇r t ≥ mt 2n ∥∇f(¯xr)∥2 − L2 2n X i∈At ∥wr i,t −¯xr∥2.(63) 23 Taking conditional expectation and summing overt, E[⟨∇f(¯xr), Gr⟩| {xr i }n i=1] (60)+(63) ≥ 1 2n Hmax−1X t=0 mt ! ∥∇f(¯xr)∥2 − L2 2n nX i=1 Hi−1X t=0 E \u0002 ∥wr i,t −¯xr∥2 {xr i }n i=1 \u0003 = ¯H 2 ∥∇f(¯xr)∥2 − L2 2n nX i=1"},{"citing_arxiv_id":"2605.18174","ref_index":60,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","primary_cat":"cs.LG","submitted_at":"2026-05-18T10:18:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18028","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FedSDR: Federated Self-Distillation with Rectification","primary_cat":"cs.LG","submitted_at":"2026-05-18T08:18:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15520","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On the Fragility of Data Attribution When Learning Is Distributed","primary_cat":"cs.LG","submitted_at":"2026-05-15T01:34:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A single adversary in distributed training inflates its attribution value via latent optimization on synthetic batches without degrading accuracy or triggering basic defenses.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11122","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement","primary_cat":"cs.CR","submitted_at":"2026-05-11T18:30:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedSurrogate defends federated learning against backdoors by clustering on security-critical layers and substituting malicious updates with benign surrogates, reporting false-positive rates below 10% and attack success below 2.1% under non-IID conditions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"trend, indicating that the detection capability ofFedSurrogatedoes not degrade as the client population grows. The MTA ofFedSurrogatedeclines from 87.92% atn= 20to 77.44% atn= 100, but the attack-free FedAvg baseline exhibits a comparable decline from 89.20% to 79.95% over the same range, confirming that the loss reflects FL convergence under finer non-IID partitioning rather than defense over-filtering [15,28]. The gap betweenFedSurrogateand undefended Fe- dAvg fluctuates between 1.21 and 3.87 percentage points with no upward trend, showing that the residual utility cost of the defense remains bounded and does not scale with the client population. Resilience to Adaptive and Layer-Aware Attacks.We evaluateFedSurro- gateunder a stronger adversarial setting where the attacker has full knowledge of"},{"citing_arxiv_id":"2605.09144","ref_index":63,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-05-09T20:03:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FedVSSAM mitigates flatness incompatibility in SAM-based federated learning by consistently using a variance-suppressed adjusted direction for local perturbation, descent, and global updates, with non-convex convergence guarantees.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"minimization seeks first-order flatness and improves generalization. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20247- 20257, June 2023. [62] Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, and Vikas Chandra. Feder- ated learning with non-iid data.arXiv preprint arXiv:1806.00582, 2018. [63] Juntang Zhuang, Boqing Gong, Liangzhe Yuan, Yin Cui, Hartwig Adam, Nicha C. Dvornek, Sekhar Tatikonda, James S. Duncan, and Ting Liu. Surrogate gap minimization improves sharpness-aware training. InInternational Conference on Learning Representations (ICLR), 2022. 14 A Additional Related Work Heterogeneous FL.FL enables collaborative training without sharing personal raw data, yet the PS"},{"citing_arxiv_id":"2605.09137","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Evaluating Federated Learning approaches for mammography under breast density heterogeneity","primary_cat":"cs.LG","submitted_at":"2026-05-09T19:44:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"FedAvg matches centralized training accuracy on mammography data split by breast density heterogeneity, showing standard FL can handle this clinical variation without special fixes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08871","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","primary_cat":"math.OC","submitted_at":"2026-05-09T10:46:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Rennala MVR improves time complexity over Rennala SGD for smooth nonconvex stochastic optimization in heterogeneous parallel systems under a mean-squared smoothness assumption.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07474","ref_index":76,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations","primary_cat":"cs.CV","submitted_at":"2026-05-08T09:20:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ForgeVLA enables federated VLA model training from unlabeled vision-action pairs by recovering language via embodied classifiers and using contrastive planning plus adaptive aggregation to avoid feature collapse.","context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"[74] Tianhe Yu, Ted Xiao, Austin Stone, Jonathan Tompson, Anthony Brohan, Su Wang, Jaspiar Singh, Clayton Tan, Jodilyn Peralta, Brian Ichter, et al. Scaling robot learning with semantically imagined experience. arXiv preprint arXiv:2302.11550, 2023. [75] Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, and Vikas Chandra. Federated learning with non-IID data.arXiv preprint arXiv:1806.00582, 2018. [76] Ruijie Zheng, Dantong Niu, Yuqi Xie, Jing Wang, Mengda Xu, Yunfan Jiang, Fernando Castañeda, Fengyuan Hu, You Liang Tan, Letian Fu, et al. Egoscale: Scaling dexterous manipulation with diverse egocentric human data.arXiv preprint arXiv:2602.16710, 2026. [77] Kaiwen Zhou and Xin Eric Wang. FedVLN: Privacy-preserving federated vision-and-language navigation."},{"citing_arxiv_id":"2605.06571","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"CLAD: A Clustered Label-Agnostic Federated Learning Framework for Joint Anomaly Detection and Attack Classification","primary_cat":"cs.LG","submitted_at":"2026-05-07T17:01:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CLAD is a clustered federated learning framework with a dual-mode architecture for joint anomaly detection and attack classification in IoT using labeled and unlabeled data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08152","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Privacy-Preserving Federated Learning: Integrating Zero-Knowledge Proofs in Scalable Distributed Architectures","primary_cat":"cs.DC","submitted_at":"2026-05-04T04:20:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A hybrid federated learning architecture using zero-knowledge proofs for computation verification retains 94.2% accuracy under adversarial conditions across 1,000 nodes.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"The verification cluster consisted of 20 'c5.4xlarge' compute- optimized instances to handle the cryptographic pairings. The nodes were tasked with training a federated XGBoost model [14] on the HIGGS dataset, a standard benchmark for high-variance classification. The dataset was partitioned non- i.i.d. across the network to simulate real-world data skew common in edge deployments [29]. To rigorously test the fault tolerance and security of the system, we randomly designated 10% of the worker nodes as \"Byzantine adversarial.\" These malicious nodes intentionally crafted poisoned gradients with inverted signs and exaggerated magnitudes, designed specifi- cally to destroy the global model's accuracy [30]. B. Results and Discussion"},{"citing_arxiv_id":"2605.02169","ref_index":15,"ref_count":2,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation","primary_cat":"cs.CV","submitted_at":"2026-05-04T02:58:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HeroCrystal achieves 33.4% mAP on cross-domain multi-camera object detection by combining one-shot diffusion-based synthetic data generation, probabilistic federated Faster R-CNN, and inconsistent-category distillation, outperforming prior privacy-preserving baselines by 2.1%.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"* Unbalanced Dataindicates that the training datasets contains unbalanced category distribution. * Multi-Class Predictionrefers to the model's ability to detect a large number of distinct classes across domains. 5 model without sharing their local private data [ 4]. A key challenge in real- world FL is data heterogeneity, as data across clients is typically highly non-IID due to differences in data sources and user behaviors [ 15]. Such non-IID characteristics can severely affect the convergence speed and final performance of the global model. To mitigate the negative effects of non-IID data, researchers have pro- posed various strategies. Some works focus on improving server-side ag- gregation and fusion algorithms, such as FedProx [ 16], which introduces a proximal term to limit divergence from the global model, and more advanced"},{"citing_arxiv_id":"2605.00970","ref_index":64,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Split and Aggregation Learning for Foundation Models Over Mobile Embodied AI Network (MEAN): A Comprehensive Survey","primary_cat":"cs.IT","submitted_at":"2026-05-01T16:44:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"The paper surveys split and aggregation learning for foundation models in 6G networks to improve efficiency, resource use, and data privacy in distributed AI.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"it difficult to meet the demands of efficient learning in dis- tributed wireless environments due to high communication overhead and significant data privacy risks [63]. AL provides a scalable solution by allowing devices to train local models and asynchronously aggregate their updates at a central server, ensuring low-latency, privacy-preserving, and energy-efficient AI training [64]. 1) The Framework and Training Process of AL In the AL framework, multiple clients (such as devices, sensors, or nodes) independently train local models and send local model updates (such as gradients or weights) to a central server, as shown in Fig. 6. The server aggregates updates from each client to form a global model and returns it to the clients."},{"citing_arxiv_id":"2605.00698","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"FedKPer: Tackling Generalization and Personalization in Medical Federated Learning via Knowledge Personalization","primary_cat":"eess.IV","submitted_at":"2026-05-01T14:36:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"FedKPer improves the generalization-personalization trade-off in medical federated learning via local knowledge personalization and selective aggregation that emphasizes reliable updates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27510","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"FMCL: Class-Aware Client Clustering with Foundation Model Representations for Heterogeneous Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-04-30T07:08:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FMCL performs one-shot class-aware client clustering in heterogeneous federated learning by deriving semantic signatures from foundation model embeddings and using cosine distance, yielding improved performance and stable clusters compared to prior methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16090","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Robust Synchronisation for Federated Learning in The Face of Correlated Device Failure","primary_cat":"cs.DC","submitted_at":"2026-04-17T14:21:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AW-PSP dynamically weights node sampling by real-time availability predictions and failure correlations to improve robustness, label coverage, and fairness in federated learning under correlated device failures.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13396","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"HierFedCEA: Hierarchical Federated Edge Learning for Privacy-Preserving Climate Control Optimization Across Heterogeneous Controlled Environment Agriculture Facilities","primary_cat":"eess.SY","submitted_at":"2026-04-15T01:53:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HierFedCEA delivers a hierarchical federated learning framework for privacy-preserving climate control optimization across heterogeneous CEA facilities, reaching 94% of centralized performance with under 1 MB communication.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10179","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Byzantine-Robust Distributed SGD: A Unified Analysis and Tight Error Bounds","primary_cat":"math.OC","submitted_at":"2026-04-11T12:17:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Unified convergence rates and tight lower bounds for Byzantine-robust distributed SGD under stochasticity and general data heterogeneity, showing local momentum reduces stochastic error floors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08056","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Automating aggregation strategy selection in federated learning","primary_cat":"cs.LG","submitted_at":"2026-04-09T10:08:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A framework automates federated learning aggregation strategy selection via LLM inference in single-trial mode and genetic search in multi-trial mode, improving robustness under non-IID data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.11307","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Client-Conditional Federated Learning via Local Training Data Statistics","primary_cat":"cs.LG","submitted_at":"2026-03-11T21:06:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Conditioning a global FL model on local PCA statistics of client data matches oracle cluster performance across heterogeneous settings and is robust to sparse data with zero added communication.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.03853","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Practical Quantum Federated Learning for Privacy-Sensitive Healthcare: Communication Efficiency and Noise Resilience","primary_cat":"quant-ph","submitted_at":"2026-03-04T09:04:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Hybrid QFL cuts quantum transmissions from 3TNMP to {3t + 2(T-t)}NMP over T rounds while preserving near-centralized convergence and improving depolarizing-noise resilience via decentralized aggregation and Steane-code QEC.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.00407","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks","primary_cat":"cs.LG","submitted_at":"2026-01-30T23:51:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Fed-Listing infers client label proportions in FedGNNs from final-layer gradients, outperforming baselines on four datasets and three architectures even in non-i.i.d. settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.13647","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"REVERB-FL: Server-Side Adversarial and Reserve-Enhanced Federated Learning for Robust Audio Classification","primary_cat":"eess.AS","submitted_at":"2025-12-15T18:40:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"REVERB-FL uses a server-side reserve set with retraining and adversarial training to reduce poisoning effects and speed convergence in federated audio classification under non-IID data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.18367","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multi-Worker Selection based Distributed Swarm Learning for Edge IoT with Non-i.i.d. Data","primary_cat":"cs.LG","submitted_at":"2025-09-22T19:47:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Introduces M-DSL algorithm for distributed swarm learning that selects workers using a new non-i.i.d. degree metric to improve convergence and accuracy under data heterogeneity, with theoretical analysis and experiments on heterogeneous datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.12318","ref_index":56,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning","primary_cat":"cs.LG","submitted_at":"2025-05-18T09:19:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Fed-TaLoRA uses task-agnostic low-rank residual adaptation with post-aggregation calibration to enable efficient federated continual fine-tuning across sequential tasks under non-IID conditions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2406.10861","ref_index":188,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"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":"support","context_text":"parameter-based methods that exchange in the parameter space, KD-based methods exchange J. ACM, Vol. 37, No. 4, Article 111. Publication date: August 2024. Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions 111:3 Table 1. KD-based FL methods are used to solve challenges in FL Privacy Non-IID Communication Personalization Feature-based [76] ✓ ✓ ✓ ✓ Parameter-based [129] ✓ Data-based [188] ✓ ✓ in the function space [ 82, 141]. This allows for the preservation of personalized knowledge be- tween different models to some extent in non-IID scenarios rather than being directly flattened or eliminated [161]. Furthermore, KD is model-agnostic [46], and clients have the flexibility to create personalization-focused models with varying architectures[56, 60, 76]."},{"citing_arxiv_id":"1909.06335","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","primary_cat":"cs.LG","submitted_at":"2019-09-13T17:26:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Non-identical data distributions degrade federated averaging accuracy on visual classification, but server momentum raises CIFAR-10 accuracy from 30.1% to 76.9% in the most skewed regimes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}