Search Results for author: Xiao Zhou

Found 11 papers, 2 papers with code

Efficient Neural Network Training via Forward and Backward Propagation Sparsification

no code implementations NeurIPS 2021 Xiao Zhou, Weizhong Zhang, Zonghao Chen, Shizhe Diao, Tong Zhang

For the latter step, instead of using the chain rule based gradient estimators as in existing methods, we propose a variance reduced policy gradient estimator, which only requires two forward passes without backward propagation, thus achieving completely sparse training.

Effective Sparsification of Neural Networks with Global Sparsity Constraint

no code implementations CVPR 2021 Xiao Zhou, Weizhong Zhang, Hang Xu, Tong Zhang

Weight pruning is an effective technique to reduce the model size and inference time for deep neural networks in real-world deployments.

Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from RGB

no code implementations CVPR 2021 Bo Sun, Junchi Yan, Xiao Zhou, Yinqiang Zheng

To reconstruct spectral signals from multi-channel observations, in particular trichromatic RGBs, has recently emerged as a promising alternative to traditional scanning-based spectral imager.

Explicit Connection Distillation

no code implementations1 Jan 2021 Lujun Li, Yikai Wang, Anbang Yao, Yi Qian, Xiao Zhou, Ke He

In this paper, we present Explicit Connection Distillation (ECD), a new KD framework, which addresses the knowledge distillation problem in a novel perspective of bridging dense intermediate feature connections between a student network and its corresponding teacher generated automatically in the training, achieving knowledge transfer goal via direct cross-network layer-to-layer gradients propagation, without need to define complex distillation losses and assume a pre-trained teacher model to be available.

Knowledge Distillation Transfer Learning

Effective Training of Sparse Neural Networks under Global Sparsity Constraint

no code implementations1 Jan 2021 Xiao Zhou, Weizhong Zhang, Tong Zhang

An appealing feature of ProbMask is that the amounts of weight redundancy can be learned automatically via our constraint and thus we avoid the problem of tuning pruning rates individually for different layers in a network.

Diversifying Dialogue Generation with Non-Conversational Text

1 code implementation ACL 2020 Hui Su, Xiaoyu Shen, Sanqiang Zhao, Xiao Zhou, Pengwei Hu, Randy Zhong, Cheng Niu, Jie zhou

Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation.

Dialogue Generation Translation

A Study of Pyramid Structure for Code Correction

no code implementations28 Jan 2020 Shan Huang, Xiao Zhou, Sang Chin

We demonstrate the implementations of pyramid encoders in both multi-layer GRU and Transformer for seq2seq tasks.

Software Engineering

Collaborative Metric Learning with Memory Network for Multi-Relational Recommender Systems

no code implementations24 Jun 2019 Xiao Zhou, Danyang Liu, Jianxun Lian, Xing Xie

The success of recommender systems in modern online platforms is inseparable from the accurate capture of users' personal tastes.

Metric Learning Recommendation Systems +1

Topic-Enhanced Memory Networks for Personalised Point-of-Interest Recommendation

2 code implementations19 May 2019 Xiao Zhou, Cecilia Mascolo, Zhongxiang Zhao

Point-of-Interest (POI) recommender systems play a vital role in people's lives by recommending unexplored POIs to users and have drawn extensive attention from both academia and industry.

Sequential Recommendation

Discovering Latent Patterns of Urban Cultural Interactions in WeChat for Modern City Planning

no code implementations14 Jun 2018 Xiao Zhou, Anastasios Noulas, Cecilia Mascoloo, Zhongxiang Zhao

Cultural activity is an inherent aspect of urban life and the success of a modern city is largely determined by its capacity to offer generous cultural entertainment to its citizens.

Heuristic Search for Structural Constraints in Data Association

no code implementations8 Nov 2017 Xiao Zhou, Peilin Jiang, Fei Wang

In this paper, we propose a new heuristic method to search for structural constraints (HSSC) of multiple targets when solving the problem of online multi-object tracking.

Multi-Object Tracking Online Multi-Object Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.