{"id":558237,"date":"2018-12-26T23:56:35","date_gmt":"2018-12-27T07:56:35","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=558237"},"modified":"2020-11-19T19:39:41","modified_gmt":"2020-11-20T03:39:41","slug":"deep-learning-and-representation-learning","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/deep-learning-and-representation-learning\/","title":{"rendered":"Deep Learning and Representation Learning"},"content":{"rendered":"

We are working on deep learning. We focus on developing new learning strategies and more efficient algorithms, designing better neural network structures, and improving representation learning.<\/p>\n

Efficient Deep Learning<\/strong>
\nXiang Li, Tao Qin, Jian Yang, and Tie-Yan Liu, LightRNN: Memory and Computation-Efficient Recurrent Neural Networks (opens in new tab)<\/span><\/a>, NIPS<\/strong> 2016. [Code@GitHub (opens in new tab)<\/span><\/a>]
\nFei Gao, Lijun Wu, Li Zhao, Tao Qin, and Tie-Yan Liu,
Efficient Sequence Learning with Group Recurrent Networks (opens in new tab)<\/span><\/a>, NAACL<\/strong> 2018.
\nZhuohan Li, Di He, Fei Tian, Wei Chen, Tao Qin, Liwei Wang, and Tie-Yan Liu,
Towards Binary-Valued Gates for Robust LSTM Training (opens in new tab)<\/span><\/a>, ICML<\/strong> 2018. [code (opens in new tab)<\/span><\/a>] [Chinese article (opens in new tab)<\/span><\/a>]<\/p>\n

Improving Representations<\/strong>
\nJun Gao, Di He, Xu Tan, Tao Qin, Liwei Wang, Tieyan Liu\uff0c
Representation Degeneration Problem in Training Natural Language Generation Models (opens in new tab)<\/span><\/a>, ICLR<\/strong> 2019.
\nChengyue Gong, Di He, Xu Tan, Tao Qin, Liwei Wang, and Tie-Yan Liu,
FRAGE: Frequency-Agnostic Word Representation (opens in new tab)<\/span><\/a>, NIPS <\/strong>2018. [code (opens in new tab)<\/span><\/a>]<\/p>\n

Advanced Learning Strategies<\/strong>
\nDi He, Yingce Xia, Tao Qin, Liwei Wang, Nenghai Yu, Tie-Yan Liu, and Wei-Ying Ma,
Dual Learning for Machine Translation (opens in new tab)<\/span><\/a>, NIPS<\/strong> 2016.
\nYingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu and Tie-Yan Liu,
Dual Supervised Learning (opens in new tab)<\/span><\/a>, ICML <\/b>2017.<\/b>
\nLijun Wu, Li Zhao, Tao Qin, and Tie-Yan Liu,
Sequence Prediction with Unlabeled Data by Reward Function Learning (opens in new tab)<\/span><\/a>, IJCAI<\/strong> 2017.
\nYingce Xia, Jiang Bian, Tao Qin, Tie-Yan Liu,
Dual Inference for Machine Learning (opens in new tab)<\/span><\/a>, IJCAI<\/strong> 2017.
\nYingce Xia, Fei Tian, Lijun Wu, Jianxin Lin, Tao Qin, and Tie-Yan Liu,
Deliberation Networks: Sequence Generation Beyond One-Pass Decoding (opens in new tab)<\/span><\/a>, NIPS<\/strong> 2017.
\nDi He, Hanqing Lu, Yingce Xia, Tao Qin, Liwei Wang, and Tie-Yan Liu,
Decoding with Value Networks for Neural Machine Translation (opens in new tab)<\/span><\/a>, NIPS<\/strong> 2017.
\nYingce Xia, Xu Tan, Fei Tian, Tao Qin, Nenghai Yu, and Tie-Yan Liu,
Model-Level Dual Learning (opens in new tab)<\/span><\/a>, ICML<\/strong> 2018.
\nYiren Wang, Yingce Xia, Tianyu He, Fei Tian, Tao Qin, ChengXiang Zhai, Tie-Yan Liu,
Multi-Agent Dual Learning (opens in new tab)<\/span><\/a>, ICLR<\/strong> 2019.
\nChengyue Gong, Xu Tan, Di He, and Tao Qin,
Sentence-wise Smooth Regularization for Sequence to Sequence Learning (opens in new tab)<\/span><\/a>, AAAI<\/strong> 2019.<\/p>\n

New Network Structures<\/strong>
\nKaitao Song, Xu Tan, Di He, Jianfeng Lu, Tao Qin, and Tie-Yan Liu,
Double Path Networks for Sequence to Sequence Learning (opens in new tab)<\/span><\/a>, COLING<\/strong> 2018.
\nJianxin Lin, Yingce Xia, Tao Qin, Zhibo Chen, and Tie-Yan Liu,
Conditional Image-to-Image Translation (opens in new tab)<\/span><\/a>, CVPR<\/strong> 2018.
\nChang Xu, Tao Qin, Yalong Bai, Gang Wang and Tie-Yan Liu, Convolutional Neural Networks for Posed and Spontaneous Expression Recognition, ICME<\/strong> 2017.<\/p>\n","protected":false},"excerpt":{"rendered":"

We are working on deep learning. We focus on developing new learning strategies and more efficient algorithms, designing better neural network structures, and improving representation learning. Efficient Deep Learning Xiang Li, Tao Qin, Jian Yang, and Tie-Yan Liu, Code@GitHub] Fei Gao, Lijun Wu, Li Zhao, Tao Qin, and Tie-Yan Liu, Efficient Sequence Learning with Group […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-558237","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Tao Qin","user_id":33871,"people_section":"Section name 1","alias":"taoqin"},{"type":"user_nicename","display_name":"Yingce Xia","user_id":37784,"people_section":"Section name 1","alias":"yinxia"},{"type":"user_nicename","display_name":"Li Zhao","user_id":36152,"people_section":"Section name 1","alias":"lizo"},{"type":"user_nicename","display_name":"Tie-Yan Liu","user_id":34431,"people_section":"Section name 1","alias":"tyliu"}],"msr_research_lab":[199560],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/558237"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/558237\/revisions"}],"predecessor-version":[{"id":558243,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/558237\/revisions\/558243"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=558237"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=558237"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=558237"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=558237"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=558237"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}