[Photo of Fei Tian]

Fei Tian (田 飞)

Mailing Address: Facebook Headquarters 1 Hacker Way Menlo Park, CA 94025
Email: XX AT YY dot com, where XX=feitia,and YY=fb

I recently moved to Facebook to act as a research scientist in machine learning.

Previously I was a researcher in the Machine Learning Group, Microsoft Research Asia (MSRA). I obtained my PhD degree in July, 2016, from the department of computer science and technology in University of Science and Technology of China, supervised by Dr.Tie-Yan Liu and Dr. Enhong Chen. Prior to that, I obtain the bachelor degree in the same department at 2011.

I mainly work on machine learning and its application in natural language processing.

Selected Publications (Full List in Google Scholar)

  • Yiren Wang, Fei Tian, Di He, Tao Qin, ChengXiang Zhai, and Tie-Yan Liu, Non Autoregressive Machine Translation with Auxiliary Regularization, Thirty-third AAAI Conference on Artificial Intelligence (AAAI-19)[poster].

  • Renqian Luo*, Fei Tian*, Tao Qin, Enhong Chen, and Tie-Yan Liu, Neural Architecture Optimization, 32th Conference on Neural Information Processing Systems (NeurIPS-18)[codes][blog]. *=equal contribution

  • Lijun Wu*, Fei Tian*, Yingce Xia, Yang Fan, Tao Qin, Jianhuang Lai, and Tie-Yan Liu, Learning to Teach with Dynamic Loss Functions 32th Conference on Neural Information Processing Systems (NeurIPS-18)[blog]. *=equal contribution

  • Lijun Wu, Fei Tian, Tao Qin, Jianhuang Lai, and Tie-Yan Liu, A Study of Reinforcement Learning for Neural Machine Translation, 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP-18)[codes].

  • Yingce Xia, Xu Tan, Fei Tian, Tao Qin, Nenghai Yu, and Tie-Yan Liu, Model-Level Dual Learning, 35th International Conference on Machine Learning (ICML-18).

  • Zhuohan Li, Di He, Fei Tian, Wei Chen, Tao Qin, Liwei Wang, and Tie-Yan Liu, Towards Binary-Valued Gates for Robust Lstm Training, 35th International Conference on Machine Learning (ICML-18)[codes].

  • Yang Fan*, Fei Tian*, Tao Qin, Xiang-Yang Li and Tie-Yan Liu, Learning to Teach, Sixth International Conference on Learning Representations (ICLR-18) *=equal contribution .

  • Lijun Wu, Fei Tian, Li Zhao, JianHuang Lai and Tie-Yan Liu, Word Attention for Sequence to Sequence Text Understanding, Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18).

  • Yingce Xia, Fei Tian, Lijun Wu, Jianxin Lin, Tao Qin, Nenghai Yu and Tie-Yan Liu, Deliberation Networks: Sequence Generation Beyond One-Pass Decoding, 31th Conference on Neural Information Processing Systems (NIPS-17)[blog][SOTA/human parity performance on WMT'17 Chinese-English translation].

  • Yingce Xia, Fei Tian, Tao Qin, Nenghai Yu and Tie-Yan Liu, Sequence Generation with Target Attention, In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017, (ECML/PKDD-17).

  • Lijun Wu, Yingce Xia, Fei Tian, Li Zhao, Tao Qin, Jianhua Lai, Tie-Yan Liu, Adversarial Neural Machine Translation, arXiv:1704.06933,2017.

  • Yiren Wang, Fei Tian, Recurrent Residual Learning for Sequence Classification, Conference on Empirical Methods in Natural Language Processing, 2016 (EMNLP-16)[codes].

  • Huazheng Wang, Fei Tian, Bin Gao, Chenjieren Zhu, Jiang Bian, Tie-Yan Liu, Solving Verbal Comprehension Questions in IQ Test by Knowledge-Powered Word Embedding, Conference on Empirical Methods in Natural Language Processing, 2016 (EMNLP-16)[media coverage].

  • Fei Tian, Bin Gao, Di He, Tie-Yan Liu, Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves, arxiv:1604.02038,2016.

  • Yitan Li, Linli Xu, Fei Tian, Liang Jiang, Xiaowei Zhong and Enhong Chen, Word Embedding Revisited: A New Representation Learning and Explicit Matrix Factorization Perspective, Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-15).

  • Fei Tian, Haifang Li, Wei Chen, Tao Qin, Enhong Chen and Tie-Yan Liu, Agent Behavior Prediction and Its Generalization Analysis, Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14).

  • Fei Tian, Bin Gao, Qing Cui, Enhong Chen and Tie-Yan Liu, Learning Deep Representations for Graph Clustering, Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14).

  • Fei Tian, Hanjun Dai, Jiang Bian, Bin Gao, Rui Zhang, Enhong Chen and Tie-Yan Liu, A Probabilistic Model for Learning Multi-Prototype Word Embeddings, Twenty-Fifth International Conference on Computational Linguistics (COLING-14)[codes].

    • Professional Activities

  • PC members: AAAI 2016/2017/2018, ACML 2017/2018, NeurIPS 2017/2018(Top 30% Reviewers)/2019, IJCAI 2018/2019, ACL 2018/2019, ICML 2018/2019, EMNLP 2018/2019, ICLR 2019

  • Journal reviewers: TKDD, NeuroComputing, TWEB, WWWJ

    • Education

  • Sep.2011 - June.2016, School of Computer Science and Technology, University of Science and Technology of China, Doctor of Philosophy (Ph.D.)

  • Sep.2007 - Jun.2011, School of Computer Science and Technology, University of Science and Technology of China, Bachelor of Engineering (B.E.)

    • Experiences

  • Oct.2012 - June.2016: Research Intern, Machine Learning Group, Microsoft Research Asia, Mentor: Dr. Tie-Yan Liu.

  • Oct.2010 - Aug.2011: Research Intern, Information Retrieval and Mining Group, Microsoft Research Asia, Mentor: Dr. Hang Li.

  • Jul.2010 - Aug.2010 : Visiting Student,  Lab of Advanced Compiling Technology, Institute of Computing Technology, Chinese Academy of Sciences.

    • Honors and Awards

  • June.2016, Excellent Graduate Student of USTC

  • Sep.2014, IBM Scholarship

  • Sep.2014, National Scholarship

  • Sep.2014, Microsoft Research Asia PhD Fellowship Nomination Award

  • Aug.2011, Microsoft Research Asia, Stars of Tomorrow Internship Award

  • Jun.2010, Google Excellence Scholarship

  • Sep.2008, Sep.2009, Sep.2010, Excellent Student Scholarship of USTC