most citedRobust Lottery Tickets for Pre-trained Language Models

17 citations · 23 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CL2022

Efficient Adversarial Training with Robust Early-Bird Tickets

Zhiheng Xi, Rui Zheng, Tao Gui +2

Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs). However, this approach is typically more expensive than tr…

cs.CV20221 cited

Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications

Andrea Cavagna, Nan Li, Alexandros Iosifidis +1

This paper aims to design robust Edge Intelligence using semantic communication for time-critical IoT applications. We systematically analyze the effect of image DCT coefficients o…

cs.CV20222 cited

Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing

Zhongtian Dong, Nan Li, Alexandros Iosifidis +1

For time-critical IoT applications using deep learning, inference acceleration through distributed computing is a promising approach to meet a stringent deadline. In this paper, we…

cs.CL202217 cited

Robust Lottery Tickets for Pre-trained Language Models

Rui Zheng, Rong Bao, Yuhao Zhou +6

Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching acc…

cs.LG2022

Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing

Nan Li, Alexandros Iosifidis, Qi Zhang

This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and Edge…

cs.LG2022

Edge-Varying Fourier Graph Networks for Multivariate Time Series Forecasting

Kun Yi, Qi Zhang, Liang Hu +4

The key problem in multivariate time series (MTS) analysis and forecasting aims to disclose the underlying couplings between variables that drive the co-movements. Considerable rec…