arXiv subjects

Zeshen Li

Publications and source records attributed to Zeshen Li.

3 recordsLinked to original sources

arXiv2026

Federated Inference for Heterogeneous LLM Communication and Collaboration

Given the limited performance and efficiency of on-device Large Language Models (LLMs), the collaborations between multiple LLMs enable desirable performance enhancements, in which data, tokens, and model weights could be shared across LLMs. This process is constrained by task-oriented QoS demands, privacy requirements, and inherent system heterogeneity. In view of the above challenge and to fully exploit the on-device inference capabilities, we present a novel federated inference framework in this position paper, termed federated refinement \texttt{FedRefine}. This framework presents a new paradigm for heterogeneous LLMs collaboratively performing inference with communicating KV caches in a privacy-preserving manner. Some numerical results are provided to highlight the superiority of \texttt{FedRefine}. Several interesting topics are also highlighted for future research. By exploring the LLM-native communications, we wish to provide a new paradigm for this broad area.

cs.DC↗

arXiv2025

Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air

Frequent parameter exchanges between clients and the edge server incur substantial communication overhead, posing a critical bottleneck in federated learning (FL). By exploiting the superposition property of wireless waveforms, over-the-air (OTA) computation enables simultaneous analog aggregation of local updates, thereby reducing communication latency and improving spectrum efficiency. However, its scalability is constrained by the limited number of available orthogonal waveform resources, which are typically far fewer than the model dimension. To address this, we propose AgeTop-$k$, an age-aware gradient sparsification strategy that performs compression through a two-stage selection process. Specifically, the edge server first selects candidate gradient entries based on their magnitudes, and then further prioritizes them according to the Age of Information (AoI), which quantifies the staleness of updates. AoI tracking is achieved efficiently by maintaining an age vector at the edge server. We derive theoretical convergence guarantees for non-convex loss functions and demonstrate the efficacy of AgeTop-$k$ through extensive simulations.

cs.DC↗

arXiv2023

Personalizing Federated Learning with Over-the-Air Computations

Federated edge learning is a promising technology to deploy intelligence at the edge of wireless networks in a privacy-preserving manner. Under such a setting, multiple clients collaboratively train a global generic model under the coordination of an edge server. But the training efficiency is often throttled by challenges arising from limited communication and data heterogeneity. This paper presents a distributed training paradigm that employs analog over-the-air computation to address the communication bottleneck. Additionally, we leverage a bi-level optimization framework to personalize the federated learning model so as to cope with the data heterogeneity issue. As a result, it enhances the generalization and robustness of each client's local model. We elaborate on the model training procedure and its advantages over conventional frameworks. We provide a convergence analysis that theoretically demonstrates the training efficiency. We also conduct extensive experiments to validate the efficacy of the proposed framework.

cs.LG↗