177 citations · 689 across the 74 of their papers we have counts for
11 papers · 1 filter
Enabling Retrain-free Deep Neural Network Pruning using Surrogate Lagrangian Relaxation
Deniz Gurevin, Shanglin Zhou, Lynn Pepin +4
Network pruning is a widely used technique to reduce computation cost and model size for deep neural networks. However, the typical three-stage pipeline, i.e., training, pruning an…
Real-Time Execution of Large-scale Language Models on Mobile
Wei Niu, Zhenglun Kong, Geng Yuan +7
Pre-trained large-scale language models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. However, the limited weight storage and comput…
SAPAG: A Self-Adaptive Privacy Attack From Gradients
Yijue Wang, Jieren Deng, Dan Guo +5
Distributed learning such as federated learning or collaborative learning enables model training on decentralized data from users and only collects local gradients, where data is p…
Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning
Bingbing Li, Zhenglun Kong, Tianyun Zhang +4
Pre-trained large-scale language models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. However, the limited weight storage and comput…
ESMFL: Efficient and Secure Models for Federated Learning
Sheng Lin, Chenghong Wang, Hongjia Li +3
Nowadays, Deep Neural Networks are widely applied to various domains. However, massive data collection required for deep neural network reveals the potential privacy issues and als…
Against Membership Inference Attack: Pruning is All You Need
Yijue Wang, Chenghong Wang, Zigeng Wang +5
The large model size, high computational operations, and vulnerability against membership inference attack (MIA) have impeded deep learning or deep neural networks (DNNs) popularit…
FTRANS: Energy-Efficient Acceleration of Transformers using FPGA
Bingbing Li, Santosh Pandey, Haowen Fang +7
In natural language processing (NLP), the "Transformer" architecture was proposed as the first transduction model replying entirely on self-attention mechanisms without using seque…
A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods
Tianyun Zhang, Xiaolong Ma, Zheng Zhan +7
To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categ…
A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework
Yifan Gong, Zheng Zhan, Zhengang Li +8
Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices. However, previous pruning methods ma…
A Multi-Agent Reinforcement Learning Approach For Safe and Efficient Behavior Planning Of Connected Autonomous Vehicles
Songyang Han, Shanglin Zhou, Jiangwei Wang +4
The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather information about their environment by vehicle-to-vehicle (V2V) communication.…
Towards an Efficient and General Framework of Robust Training for Graph Neural Networks
Kaidi Xu, Sijia Liu, Pin-Yu Chen +4
Graph Neural Networks (GNNs) have made significant advances on several fundamental inference tasks. As a result, there is a surge of interest in using these models for making poten…