29 citations · 32 across the 10 of their papers we have counts for
8 papers · 1 filter
Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention
Qijun Hou, Yuchen Shi, Pingyi Fan +1
Federated learning relies on effective client selection to alleviate the performance degradation caused by data heterogeneity. Most existing methods assume full visibility of all c…
FedGMI: Generative Model-Driven Federated Learning for Probabilistic Mixture Inference
Qijun Hou, Yuchen Shi, Pingyi Fan +1
Federated Learning (FL) facilitates collaborative model training across decentralized clients while preserving data privacy by avoiding raw data exchange. Despite its potential, FL…
EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks
Yuchen Shi, Qijun Hou, Pingyi Fan +1
Federated Learning (FL) has emerged as a transformative distributed learning paradigm in the era of Internet of Things (IoT), reconceptualizing data processing methodologies. Howev…
Exploring Critical Testing Scenarios for Decision-Making Policies: An LLM Approach
Weichao Xu, Huaxin Pei, Jingxuan Yang +3
Recent advances in decision-making policies have led to significant progress in fields such as autonomous driving and robotics. However, testing these policies remains crucial with…
Towards Fault Tolerance in Multi-Agent Reinforcement Learning
Yuchen Shi, Huaxin Pei, Liang Feng +2
Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to e…
FedNC: A Secure and Efficient Federated Learning Method with Network Coding
Yuchen Shi, Zheqi Zhu, Pingyi Fan +2
Federated Learning (FL) is a promising distributed learning mechanism which still faces two major challenges, namely privacy breaches and system efficiency. In this work, we reconc…
FedLP: Layer-wise Pruning Mechanism for Communication-Computation Efficient Federated Learning
Zheqi Zhu, Yuchen Shi, Jiajun Luo +4
Federated learning (FL) has prevailed as an efficient and privacy-preserved scheme for distributed learning. In this work, we mainly focus on the optimization of computation and co…
ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Sampling
Zheqi Zhu, Yuchen Shi, Pingyi Fan +2
As a promising learning paradigm integrating computation and communication, federated learning (FL) proceeds the local training and the periodic sharing from distributed clients. D…