42 citations · 161 across the 16 of their papers we have counts for
16 papers
RPTQ: Reorder-based Post-training Quantization for Large Language Models
Zhihang Yuan, Lin Niu, Jiawei Liu +7
Large-scale language models (LLMs) have demonstrated impressive performance, but their deployment presents challenges due to their significant memory usage. This issue can be allev…
Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance
Zhihang Yuan, Jiawei Liu, Jiaxiang Wu +6
Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures. Despite its e…
A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection
Bingzhe Wu, Jintang Li, Junchi Yu +17
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite t…
PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization
Zhihang Yuan, Chenhao Xue, Yiqi Chen +2
Quantization is one of the most effective methods to compress neural networks, which has achieved great success on convolutional neural networks (CNNs). Recently, vision transforme…
PTQ-SL: Exploring the Sub-layerwise Post-training Quantization
Zhihang Yuan, Yiqi Chen, Chenhao Xue +3
Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which a…
Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention
Zhe Zhou, Junlin Liu, Zhenyu Gu +1
In recent years, transformer models have revolutionized Natural Language Processing (NLP) and shown promising performance on Computer Vision (CV) tasks. Despite their effectiveness…
GNNSampler: Bridging the Gap between Sampling Algorithms of GNN and Hardware
Xin Liu, Mingyu Yan, Shuhan Song +5
Sampling is a critical operation in Graph Neural Network (GNN) training that helps reduce the cost. Previous literature has explored improving sampling algorithms via mathematical…
Customizing Trusted AI Accelerators for Efficient Privacy-Preserving Machine Learning
Peichen Xie, Xuanle Ren, Guangyu Sun
The use of trusted hardware has become a promising solution to enable privacy-preserving machine learning. In particular, users can upload their private data and models to a hardwa…
ENAS4D: Efficient Multi-stage CNN Architecture Search for Dynamic Inference
Zhihang Yuan, Xin Liu, Bingzhe Wu +1
Dynamic inference is a feasible way to reduce the computational cost of convolutional neural network(CNN), which can dynamically adjust the computation for each input sample. One o…
S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
Zhihang Yuan, Bingzhe Wu, Zheng Liang +3
Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight p…
Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
Bingzhe Wu, Chaochao Chen, Shiwan Zhao +6
Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD)…
Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
Bingzhe Wu, Shiwan Zhao, ChaoChao Chen +5
In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove th…
BAYHENN: Combining Bayesian Deep Learning and Homomorphic Encryption for Secure DNN Inference
Peichen Xie, Bingzhe Wu, Guangyu Sun
Recently, deep learning as a service (DLaaS) has emerged as a promising way to facilitate the employment of deep neural networks (DNNs) for various purposes. However, using DLaaS a…
P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification
Bingzhe Wu, Shiwan Zhao, Guangyu Sun +4
Recently, deep convolutional neural networks (CNNs) have achieved great success in pathological image classification. However, due to the limited number of labeled pathological ima…
G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification
Bingzhe Wu, Xiaolu Zhang, Shiwan Zhao +4
Pathological glomerulus classification plays a key role in the diagnosis of nephropathy. As the difference between different subcategories is subtle, doctors often refer to slides…
SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution
Bingzhe Wu, Haodong Duan, Zhichao Liu +1
Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the…