{"total":36,"items":[{"citing_arxiv_id":"2607.00252","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Distributionally Robust Linear Regression With Block Lewis Weights","primary_cat":"cs.LG","submitted_at":"2026-06-30T23:01:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Algorithm for group distributionally robust linear regression using block Lewis weights to achieve (1+ε) optimality in Õ(min{rank(A), m}^{1/3} ε^{-2/3}) linear-system solves.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30499","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-06-29T16:02:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Random Network Distillation enables pre-training discovery of client clusters in federated learning via local novelty signals, supporting autonomous grouping under non-IID data without a priori cluster count.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28493","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Role of Artificial Intelligence in the SKA Era","primary_cat":"astro-ph.IM","submitted_at":"2026-06-26T18:00:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"This review chapter maps SKA data volume, complexity, and interpretability challenges onto deep learning, generative models, reinforcement learning, and federated learning for source detection, calibration, and discovery.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27622","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks","primary_cat":"cs.LG","submitted_at":"2026-06-26T00:37:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"FoggyTrust is a hierarchical extension of FLTrust that localizes trust computation to fog nodes and combines it with heterogeneity-aware optimizers, reporting over 50% gains on CIFAR-10 under Krum and Trim attacks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23500","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Development and Design of FLKit: A Structured Onboarding Toolkit for Federated Learning in Health and Life Sciences","primary_cat":"cs.DC","submitted_at":"2026-06-22T15:46:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FLKit is a new toolkit with four lifecycle stages, eleven role-specific entry points, a glossary, FL Story template, and tool directory to support federated learning projects in health and life sciences.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23091","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FLFL: Federated Latent Factor Learning for Private Recovery of Spatio-Temporal Signals","primary_cat":"cs.LG","submitted_at":"2026-06-22T09:38:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"FLFL extends latent factor learning into a federated framework that recovers missing spatio-temporal signals in wireless sensor networks by sharing gradients and enforcing spatio-temporal regularization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22928","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HADES: Privacy-Preserving Federated Learning via Selective Feature Encryption and Hybrid Model Fusion","primary_cat":"cs.CR","submitted_at":"2026-06-22T07:05:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HADES selectively encrypts privacy-sensitive features identified by PCA in federated learning, trains hybrid encrypted and plaintext networks, and fuses them to match vanilla FL accuracy with reduced overhead and better privacy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18758","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EH-FedSAG: Variance-Reduced Federated Learning with Energy-Aware Participation in Energy-Harvesting IoT","primary_cat":"eess.SP","submitted_at":"2026-06-17T07:11:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"EH-FedSAG achieves higher test accuracy and lower training variance than EH-FedAvg in simulations of energy-harvesting federated learning for both homogeneous and heterogeneous data, with larger gains under scarce energy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18003","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift","primary_cat":"cs.LG","submitted_at":"2026-06-16T14:50:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"C2FL proposes spatial clustering plus continual learning techniques inside federated learning to maintain performance under combined spatial heterogeneity and temporal drift.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12963","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ScaleAcross: Designing Multi-Data-Center Infrastructure for Geo-Distributed AI Training","primary_cat":"cs.NI","submitted_at":"2026-06-11T06:48:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Presents an EVPN-VXLAN emulation framework with ECMP, BFD, and queue-pair traffic distribution for studying AllReduce and Parameter Server patterns in geo-distributed AI training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11712","ref_index":60,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Substrate Asymmetry in User-Side Memory: A Diagnostic Framework","primary_cat":"cs.CL","submitted_at":"2026-06-10T06:39:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"User memory in LLMs factors into three orthogonal axes where parametric adapters and retrieval show opposite strengths, with causal evidence from attention interventions and an alignment tax on RLHF models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29587","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FPLIER: Federated Pathway-Level Information Extractor","primary_cat":"q-bio.QM","submitted_at":"2026-05-28T08:30:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FPLIER performs federated PLIER training via secure aggregation that is algebraically equivalent to centralized training, with membership-inference risk shown to decrease as the rank of the expression matrix increases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28764","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks","primary_cat":"cs.AI","submitted_at":"2026-05-27T17:23:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"SwarmHarness is a proposed decentralized protocol for compute sharing among AI agents via DHT registry, load-aware routing, and credit incentives that penalize non-contributors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20866","ref_index":238,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":"2605.19145","ref_index":12,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks","primary_cat":"cs.LG","submitted_at":"2026-05-18T21:53:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PMF-CL derives Pareto-minimal-forgetting algorithms for linear/basis-function regression and quadratic-bounded losses like logistic regression, achieving static O(d²) memory for d-parameter models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18647","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Federated Naive Bayes with Real Mixture of Gaussians and Institutional Governance Regularization for Network Intrusion Detection","primary_cat":"cs.CR","submitted_at":"2026-05-18T16:54:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A federated intrusion detection method combines hybrid Naive Bayes classifiers as a mixture of Gaussians and uses a governance-derived Institutional Coherence Index to regularize server-side weights via Nelder-Mead optimization, reporting F1 gains over size-proportional averaging on three datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27416","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Can Quantum Federated Learning Withstand Circuit-Level Backdoors?","primary_cat":"quant-ph","submitted_at":"2026-05-18T12:36:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces the CULT threat model with four circuit-level attacks on quantum federated learning and shows they degrade accuracy on MNIST and CIFAR-10 even when defenses like Krum are used.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18174","ref_index":237,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":"2605.14886","ref_index":12,"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":"2605.10404","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Position: Life-Logging Video Streams Make the Privacy-Utility Trade-off Inevitable","primary_cat":"cs.CV","submitted_at":"2026-05-11T11:42:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Life-logging video streams create an inevitable privacy-utility trade-off that is a foundational challenge for always-on AI systems.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"In this process, end users capture their desired raw data by cameras and/or sensors. End users (humans) is able to extract sensitive information mentioned in Section II.B from these raw data. On-device Storage and Process.In this part, captured raw data remain on the user-side. At first glance, this process is safe. However, this does not hold for individuals unaware of being recorded, such as pedestrians on the road [54]. If maliciously exploited, sensitive personal information, such as those summarized in Section II.B, of these appeared individuals can be inferred from the raw data. Transmit and Upload.We focus on uploading data to remote servers in this part. Transmitting raw data, as mentioned in Section II.B, directly exposes private information of end users and recorded individuals such as identity,"},{"citing_arxiv_id":"2605.08871","ref_index":235,"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":"2605.07860","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems","primary_cat":"cs.LG","submitted_at":"2026-05-08T15:20:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Experiments on real industrial time series show that partial model sharing improves diffusion model performance in bandwidth-limited non-IID settings, while full sharing stabilizes GAN training but offers less robustness than VAE or DDPM alternatives.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Thevalidationstage individually estimates personalized anomaly thresholdϵ c for each client. Finally, duringtesting, the clients evaluate the performance on the new time series data. transfer of large models or frequent updates [10]. These challenges motivate the integration of genera- tive AD with ownership-preserving data management and communication-efficient training paradigms - most notably, Federated Learning (FL)[11], [12]. While FL has been studied widely for classification or regression tasks, its adaptation to generative models - and in particular, for time series AD - remains largely unexplored [13], [14]. This gap highlights the need for a systematic evaluation of generative modeling in federated settings tailored to industrial IoT and PdM scenarios. Such an evaluation should consider not only detection perfor-"},{"citing_arxiv_id":"2605.06820","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Overcoming data scarcity through multi-center federated learning for organs-at-risk segmentation in pediatric upper abdominal radiotherapy","primary_cat":"physics.med-ph","submitted_at":"2026-05-07T18:21:43+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Federated learning on 310 CT scans from two centers yields pediatric OAR segmentation models with better cross-center robustness than local models for nine evaluated structures.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00970","ref_index":70,"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":"devices, it can only access the aggregated results without viewing individual device updates. 3) AL in Wireless Communication Networks AL provides several benefits for wireless communication networks. By transmitting model updates instead of raw data, it significantly reduces communication overhead, making it ideal for bandwidth-constrained environments [70]. Its scala- bility and flexibility make it suitable for large-scale, privacy- sensitive applications such as smart healthcare, industrial au- tomation, and edge AI deployments [71]. Furthermore, AL enhances privacy by keeping sensitive user data localized, reducing the risks associated with data breaches and unau- thorized access [72]. Despite its advantages, AL faces several challenges in"},{"citing_arxiv_id":"2604.26388","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SplitFT: An Adaptive Federated Split Learning System For LLMs Fine-Tuning","primary_cat":"cs.DC","submitted_at":"2026-04-29T07:58:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SplitFT adapts cut-layer selection and reduces LoRA rank per client in federated split learning to improve efficiency and performance when fine-tuning LLMs on heterogeneous devices and data.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"\"Communication-efficient learning of deep networks from decentralized data,\" 2023. [Online]. Available: https://arxiv.org/abs/1602.05629 [29] X. Zhang and W. Chen, \"Theoretical analysis of privacy leakage in trustworthy federated learning: A perspective from linear algebra and optimization theory,\" 2024. [Online]. Available: https://arxiv.org/abs/2407.16735 [30] P. Lu, X. Meng, and X. Liu, \"Fedcmk: An efficient privacy-preserving federated learning framework,\" inArtificial Intelligence Security and Privacy, J. Vaidya, M. Gabbouj, and J. Li, Eds. Singapore: Springer Nature Singapore, 2024, pp. 253-271. [31] T. H. Rafi, F. A. Noor, T. Hussain, and D.-K. Chae, \"Fairness and privacy-preserving in federated learning: A survey,\" 2023."},{"citing_arxiv_id":"2604.21585","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scalable Multimodal Beam Alignment in V2X: An Anti-Imbalance Graph Learning Approach","primary_cat":"eess.SP","submitted_at":"2026-04-23T12:05:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A multimodal graph learning method for V2X beam alignment cuts overhead by over 90% and outperforms prior federated learning baselines under label and modality imbalance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21428","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Decoupled DiLoCo for Resilient Distributed Pre-training","primary_cat":"cs.CL","submitted_at":"2026-04-23T08:45:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Decoupled DiLoCo enables asynchronous distributed pre-training with zero global downtime under simulated failures while preserving competitive performance on text and vision tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11562","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Impact of Federated Learning on Distributed Remote Sensing Archives","primary_cat":"cs.CV","submitted_at":"2026-04-13T14:46:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"FedProx outperforms FedAvg for deeper models under data heterogeneity, BSP reaches near-centralized accuracy at high communication cost, and LeNet gives the best accuracy-communication trade-off on the UC Merced dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10778","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Pseudoconvex Problems in Operational Decision Systems: Algorithms for Joint Learning and Optimization","primary_cat":"math.OC","submitted_at":"2026-04-12T19:02:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Iterative joint learning-optimization framework with convergent algorithms for pseudoconvex objectives in operational decision systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07125","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation","primary_cat":"cs.CR","submitted_at":"2026-04-08T14:19:39+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.00418","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Secure, Verifiable, and Scalable Multi-Client Data Sharing via Consensus-Based Privacy-Preserving Data Distribution","primary_cat":"cs.CR","submitted_at":"2026-01-01T18:12:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CPPDD is a new consensus-based protocol for privacy-preserving multi-client data sharing that achieves unanimous-release confidentiality, linear scalability, and high-probability malicious deviation detection.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.18367","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":"2504.04678","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Assumptions: Measuring Federated Learning over Real 5G Networks","primary_cat":"cs.NI","submitted_at":"2025-04-07T02:19:01+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Real 5G testbed experiments show consistent stragglers in 70% of federated learning trials due to communication delays, challenging common wireless FL assumptions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2405.07406","ref_index":158,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Machine Unlearning: A Comprehensive Survey","primary_cat":"cs.CR","submitted_at":"2024-05-13T00:58:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A survey classifying machine unlearning into centralized (exact and approximate), distributed/irregular data, verification, and privacy/security categories with technique overviews.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"unlearning, diffusion model unlearning, and large language model unlearning. 6.1 Federated Unlearning FL was initially introduced to protect the privacy of participating clients during the machine learning training process in distributed settings. All participants will only upload their locally trained model parameters instead of their sensitive local data to the FL server during model training processes [ 158]. Therefore, in a federated learning scenario, limited access to the dataset will become a unique challenge when implementing unlearning. According to the unlearning target of a whole client's contribution or samples' contribution, we can roughly divide existing unlearning studies into two categories: client-level and sample-level federated unlearning."},{"citing_arxiv_id":"2101.00190","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","primary_cat":"cs.CL","submitted_at":"2021-01-01T08:00:36+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Prefix-tuning matches or exceeds fine-tuning on NLG tasks by optimizing a continuous prefix using 0.1% of parameters while keeping the LM frozen.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.11367","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Data Aggregation Techniques for Internet of Things","primary_cat":"cs.NI","submitted_at":"2019-07-24T18:21:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"Proposes three approaches for IoT data aggregation: D2D-based clustering for energy efficiency in stationary/mobile nodes, a scheme to improve quality of uncertain raw data, and a prediction-based framework for massive medical IoT devices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}