25 citations · 130 across the 24 of their papers we have counts for
7 papers · 1 filter
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)…
Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis
Mengting Hu, Shiwan Zhao, Honglei Guo +2
Aspect-based sentiment analysis (ABSA) is to predict the sentiment polarity towards a particular aspect in a sentence. Recently, this task has been widely addressed by the neural a…
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…
Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification
Mengting Hu, Yike Wu, Shiwan Zhao +3
Cross-domain sentiment classification has drawn much attention in recent years. Most existing approaches focus on learning domain-invariant representations in both the source and t…
Improving Captioning for Low-Resource Languages by Cycle Consistency
Yike Wu, Shiwan Zhao, Jia Chen +3
Improving the captioning performance on low-resource languages by leveraging English caption datasets has received increasing research interest in recent years. Existing works main…
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…