{"total":24,"items":[{"citing_arxiv_id":"2606.30615","ref_index":129,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage","primary_cat":"stat.ME","submitted_at":"2026-06-29T17:49:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proposes a covariance-aware tuning-free shrinkage framework and sequential algorithm for multi-source estimation that attains oracle risk asymptotically and improves on single-step methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26243","ref_index":45,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks","primary_cat":"cs.LG","submitted_at":"2026-05-25T18:10:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CE-FedGNN enables federated GNN training on coupled distributed graphs via infrequent aggregated representation exchange, moving-average estimation for staleness, and metric-DP, with O(1/sqrt(T)) convergence and O(T^{3/4}) communication.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24545","ref_index":26,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Rethinking Federated Unlearning via the Lens of Memorization","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:25:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces Grouped Memorization Evaluation and FedMemPrune to remove unique memorized information in federated unlearning while preserving overlapping knowledge.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21322","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"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":"2605.20866","ref_index":145,"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":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18174","ref_index":143,"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":"2605.17778","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models","primary_cat":"math.ST","submitted_at":"2026-05-18T02:56:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"s-step self-distillation is optimal among spectral shrinkage estimators for s-spiked covariance matrices and necessary for optimality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13434","ref_index":252,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:27:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Rescaled ASGD recovers convergence to the true global objective by rescaling worker stepsizes proportional to computation times, matching the known time lower bound in the leading term under non-convex smoothness and bounded heterogeneity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09137","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":141,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":"2605.06987","ref_index":220,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Response Time Enhances Alignment with Heterogeneous Preferences","primary_cat":"cs.LG","submitted_at":"2026-05-07T22:05:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00970","ref_index":73,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":"reducing the risks associated with data breaches and unau- thorized access [72]. Despite its advantages, AL faces several challenges in practical applications. Model bias can affect fairness and generalization, particularly when client data is highly imbal- anced. Communication overhead remains a concern, as large- scale participation can still lead to bandwidth congestion and latency [73]. Integrating AL with 6G requires optimizing ag- gregation efficiency and ensuring stability in dynamic environ- ments [48]. Furthermore, while asynchronous updates enhance adaptability, they may slow convergence. Continued research is essential to refine aggregation strategies and improve AL's efficiency in 5G and 6G networks [74]. In the era of 6G wireless networks, AL has emerged as"},{"citing_arxiv_id":"2604.26604","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Who Trains Matters: Federated Learning under Enrollment and Participation Selection Biases","primary_cat":"cs.LG","submitted_at":"2026-04-29T12:33:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A two-stage selection model for federated learning permits inverse probability weighting to recover the target-population mean update under ignorability and positivity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10179","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":"2604.09489","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers","primary_cat":"cs.CR","submitted_at":"2026-04-10T16:54:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"XFED is the first aggregation-agnostic non-collusive model poisoning attack that bypasses eight state-of-the-art defenses on six benchmark datasets without attacker coordination.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.03330","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AICCE: AI Driven Compliance Checker Engine","primary_cat":"cs.CR","submitted_at":"2026-04-03T00:45:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"AICCE combines RAG-based retrieval of protocol specs with dual LLM pipelines for debate-driven explanations or fast script execution, reporting up to 99% accuracy on IPv6 samples.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"In multiagent AI systems, multiple intelligent agents col- laborate (or sometimes compete) to accomplish tasks whose complexity may surpass the capability of a single agent. Each agent acts on local observations yet may also exchange information or learned parameters to enhance collective out- comes [28]. This paradigm has proven effective in highly distributed settings such as federated learning [29], where data is scattered across different nodes or devices and must be processed without compromising privacy. Multiagent rein- forcement learning (RL-MAS) extends single-agent RL prin- ciples to shared environments with multiple decision-makers [30]. Agents iteratively refine their policies via trial and error, adapting to evolving conditions and the actions of other agents."},{"citing_arxiv_id":"2604.02370","ref_index":90,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey on AI for 6G: Challenges and Opportunities","primary_cat":"cs.NI","submitted_at":"2026-03-30T08:22:50+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":1.0,"formal_verification":"none","one_line_summary":"AI techniques including deep learning, reinforcement learning, and federated learning are positioned to enable high data rates, low latency, and massive connectivity in 6G networks while addressing scalability, security, and energy challenges.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"observable Markov decision process (POMDP) formulations, recurrent policies, and adversarial training for robustness. Non-stationarity in traffic and interference calls for re- play buffers, curriculum learning, and meta -RL techniques, while safety and service -level agreement (SLA) compli - ance necessitate constrained RL or offline-to-online learning pipelines [90], [91]. In practice, different RL approaches excel in different operational regimes. DQN and dueling DQN are efficient and stable for discrete action spaces with limited coupling, mak - ing them suitable for PRB scheduling. PPO, TD3, and DDPG perform well for continuous or smooth control tasks, with PPO often exhibiting greater stability under strict real -time"},{"citing_arxiv_id":"2603.05116","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-03-05T12:37:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FedBCGD reduces communication in federated learning by a factor of 1/N through block-wise parameter updates with accelerated convergence guarantees.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.18632","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multi-user Pufferfish Privacy","primary_cat":"cs.CR","submitted_at":"2025-12-21T08:06:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Sufficient conditions using the Wasserstein metric of order 1 are derived to calibrate Laplace noise for pufferfish privacy in multi-user aggregated queries, with relaxations for binary data that reduce noise while preserving indistinguishability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2504.13850","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FedOptima: Optimizing Resource Utilization in Federated Learning","primary_cat":"cs.DC","submitted_at":"2025-03-10T20:23:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"UNKNOWN","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FedOptima reduces both straggler and dependency idle times in federated learning via layer offloading, asynchronous aggregation, auxiliary networks, and server scheduling, delivering up to 21.8x faster training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2310.11203","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Federated Learning with Nonvacuous Generalisation Bounds","primary_cat":"cs.LG","submitted_at":"2023-10-17T12:29:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"UNKNOWN","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Federated learning trains private local randomised predictors whose aggregation yields a global predictor with nonvacuous PAC-Bayesian generalisation bounds and near-centralized accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.02441","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Semantic-Effectiveness Filtering and Control for Post-5G Wireless Connectivity","primary_cat":"cs.NI","submitted_at":"2019-07-04T14:58:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces a semantic-effectiveness (SE) plane to augment protocol stacks with standardized interfaces for semantic filtering and cross-layer control in post-5G wireless systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.10718","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Active Learning Solution on Distributed Edge Computing","primary_cat":"cs.DC","submitted_at":"2019-06-25T18:27:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A hybrid approach applies active learning at edge devices and federated learning at fog nodes to reduce training data volume and communication cost for image classification in distributed edge-fog setups.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1610.05492","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Federated Learning: Strategies for Improving Communication Efficiency","primary_cat":"cs.LG","submitted_at":"2016-10-18T09:11:51+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Structured updates (low-rank or masked) and sketched updates (quantized, rotated, subsampled) reduce uplink communication in federated learning by up to two orders of magnitude on convolutional and recurrent networks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Ananda Theertha Suresh, Felix X. Yu, Sanjiv Kumar, and H. Brendan McMahan. Distributed mean estimation with limited communication. In Proceedings of the 34th International Conference on Machine Learning , pp. 3329-3337, 2017. David P. Woodruff. Sketching as a tool for numerical linear algebra. Foundations and Trends in Theoretical Computer Science, 10(12):1-157, 2014. ISSN 1551-305X. doi: 10.1561/0400000060. Yuchen Zhang and Xiao Lin. DiSCO: Distributed optimization for self-concordant empirical loss. In ICML, pp. 362-370, 2015. 10"}],"limit":50,"offset":0}