127 citations · 559 across the 76 of their papers we have counts for
12 papers · 1 filter
GA-DRL: Graph Neural Network-Augmented Deep Reinforcement Learning for DAG Task Scheduling over Dynamic Vehicular Clouds
Zhang Liu, Lianfen Huang, Zhibin Gao +3
Vehicular clouds (VCs) are modern platforms for processing of computation-intensive tasks over vehicles. Such tasks are often represented as directed acyclic graphs (DAGs) consisti…
Magnitude Matters: Fixing SIGNSGD Through Magnitude-Aware Sparsification in the Presence of Data Heterogeneity
Richeng Jin, Xiaofan He, Caijun Zhong +3
Communication overhead has become one of the major bottlenecks in the distributed training of deep neural networks. To alleviate the concern, various gradient compression methods h…
Mobility, Communication and Computation Aware Federated Learning for Internet of Vehicles
Md Ferdous Pervej, Jianlin Guo, Kyeong Jin Kim +7
While privacy concerns entice connected and automated vehicles to incorporate on-board federated learning (FL) solutions, an integrated vehicle-to-everything communication with het…
Neural Tangent Kernel Empowered Federated Learning
Kai Yue, Richeng Jin, Ryan Pilgrim +3
Federated learning (FL) is a privacy-preserving paradigm where multiple participants jointly solve a machine learning problem without sharing raw data. Unlike traditional distribut…
Federated Learning via Plurality Vote
Kai Yue, Richeng Jin, Chau-Wai Wong +1
Federated learning allows collaborative workers to solve a machine learning problem while preserving data privacy. Recent studies have tackled various challenges in federated learn…
Adversarial training may be a double-edged sword
Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, Huaiyu Dai
Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box…