distributed-learning

SeFoRA is a proposed federated LoRA algorithm that uses sketch aggregation to handle heterogeneous client ranks and alleviate bilinear mismatch. It includes a rank-homogeneous variant with convergence guarantees and shows state-of-the-art performance on RoBERTa-Large fine-tuning.

Introduces VRDQ, a decentralized Q-learning algorithm for multi-agent reinforcement learning over static and time-varying networks, with finite-time convergence guarantees that achieve linear speedups in sample complexity with only Õ(1) communication.

This paper proposes DUQFL-Prox, a drift-stable quantum federated learning framework that uses deep-unfolded local optimization with adaptive SPSA updates and a proximal term to improve stability, generalization, and client fairness in heterogeneous distributed environments.

FedOPAL proposes a framework that adapts visual prompts as feature rectifiers for one-shot federated learning, achieving efficient gradient-free aggregation via analytic methods while outperforming existing analytical approaches and matching iterative methods with zero server-side training costs.

Applies federated learning to object detection for drone fleets, enabling collaborative training without centralizing aerial imagery, achieving performance close to centralized training while preserving privacy and reducing bandwidth.

This paper proposes the first FTRL-type algorithms for decentralized online convex optimization with compressed communication, achieving elegant theoretical guarantees and improved regret bounds compared to previous OGD-type methods.

This paper reveals a non-monotonic effect of privacy on generalization error in Byzantine-robust distributed learning: in high-noise (strong privacy) regimes, increasing privacy reduces generalization error, while in low-noise (weaker privacy) regimes, increasing privacy degrades generalization.

FoggyTrust is a hierarchical extension of FLTrust that localizes trust computation to fog nodes, improving robustness against Byzantine attacks in heterogeneous federated learning settings, achieving over 50% improvement on challenging attacks like Krum and Trim on CIFAR-10.

This paper presents a vision for integrating multi-modal multi-task federated foundation models (M3T FedFMs) into vehicular networks, discussing training principles, use cases, challenges, and a case study on the Waymo Open Dataset.

This paper proposes MODIAD, a framework for multimodal online distributed industrial anomaly detection, addressing resource constraints with a Multi-class Intelligent Scheduling problem and a Resource Efficient Class-Wise Low Rank Adaptation (REC-LoRA) strategy. Experiments on MVTec 3D-AD and Eyecandies datasets demonstrate superior performance and efficiency.

This paper introduces 'dictator clients'—a novel class of malicious participants in federated learning capable of erasing other clients' contributions while preserving their own—and provides theoretical analysis of their impact on model convergence, including scenarios with multiple adversarial clients.