Shiyu Chang

Research Scientist, Ph.D.

MIT-IBM Watson AI Lab

shiyu.chang [AT] ibm.com

Bio

Shiyu Chang is a research scientist at the MIT-IBM Watson AI Lab, working closely with Prof. Regina Barzilay and Prof. Tommi S. Jaakkola. He works on machine learning and its applications in natural language processing and computer vision.

His long-term research objective is to establish more efficient two-way communication mechanisms between humans and machine learning systems. In particular, he has been studying how machine predictions can be made more interpretable to humans, and how human intuition and rationalization can inform machine learning systems to improve their transferability, data inefficiency, and adversarial vulnerability issues.

Prior to his current position, Shiyu was a research scientist at the IBM T.J. Watson Research Center. He got his B.S., M.S., and Ph.D. all from the University of Illinois at Urbana-Champaign. His Ph.D. advisor is Prof. Thomas S. Huang.

Publications

Full publications on Google Scholar.
indicates authors with equal contribution. indicates my interns or the students I co-advised.

Few-shot Text Classification with Distributional Signatures

Yujia Bao☆ ‡, Menghua Wu☆ ‡, Shiyu Chang, Regina Barzilay

Arxiv Preprint

A Game Theoretic Approach to Class-wise Selective Rationalization

Shiyu Chang, Yang Zhang, Mo Yu, Tommi S. Jaakkola

NeurIPS'19: Advances in Neural Information Processing Systems

A Stratified Approach to Robustness for Randomly Smoothed Classifiers

Guang-He Lee, Yang Yuan, Shiyu Chang, Tommi S. Jaakkola

NeurIPS'19: Advances in Neural Information Processing Systems

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control

Mo Yu, Shiyu Chang, Yang Zhang, Tommi S. Jaakkola

EMNLP'19: Conference on Empirical Methods in Natural Language Processing

AutoGAN: Neural Architecture Search for Generative Adversarial Networks

Xinyu Gong, Shiyu Chang, Yifan Jiang, Zhangyang Wang

ICCV'19: International Conference on Computer Vision

Deriving Machine Attention from Human Rationales

Yujia Bao, Shiyu Chang, Mo Yu, Regina Barzilay

EMNLP'18: Conference on Empirical Methods in Natural Language Processing

Dilated Recurrent Neural Networks

Shiyu Chang, Yang Zhang, Wei Han, Mo Yu, Xiaoxiao Guo, Wei Tan, Xiaodong Cui, Michael Witbrock, Mark A. Hasegawa-Johnson, Thomas S. Huang

NIPS'17: Advances in Neural Information Processing Systems

Few-shot Text Classification with Distributional Signatures

Yujia Bao☆ ‡, Menghua Wu☆ ‡, Shiyu Chang, Regina Barzilay

Arxiv Preprint

A Game Theoretic Approach to Class-wise Selective Rationalization

Shiyu Chang, Yang Zhang, Mo Yu, Tommi S. Jaakkola

NeurIPS'19: Advances in Neural Information Processing Systems

A Stratified Approach to Robustness for Randomly Smoothed Classifiers

Guang-He Lee, Yang Yuan, Shiyu Chang, Tommi S. Jaakkola

NeurIPS'19: Advances in Neural Information Processing Systems

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control

Mo Yu, Shiyu Chang, Yang Zhang, Tommi S. Jaakkola

EMNLP'19: Conference on Empirical Methods in Natural Language Processing

AutoGAN: Neural Architecture Search for Generative Adversarial Networks

Xinyu Gong, Shiyu Chang, Yifan Jiang, Zhangyang Wang

ICCV'19: International Conference on Computer Vision

Coupled Variational Recurrent Collaborative Filtering

Qingquan Song, Shiyu Chang, Xia Hu

KDD'19: ACM SIGKDD Conference on Knowledge Discovery and Data Mining

AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Mark A. Hasegawa-Johnson

ICML'19: International Conference on Machine Learning

Hybrid Reinforcement Learning with Expert State Sequences

Xiaoxiao Guo, Shiyu Chang, Mo Yu, Gerald Tesauro, Murray Campbell

AAAI'19: AAAI Conference on Artificial Intelligence

Deriving Machine Attention from Human Rationales

Yujia Bao, Shiyu Chang, Mo Yu, Regina Barzilay

EMNLP'18: Conference on Empirical Methods in Natural Language Processing

Improving Reinforcement Learning Based Image Captioning with Natural Language Prior

Tszhang Guo, Shiyu Chang, Mo Yu, Kun Bai

EMNLP'18: Conference on Empirical Methods in Natural Language Processing

One-Shot Relational Learning for Knowledge Graphs

Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

EMNLP'18: Conference on Empirical Methods in Natural Language Processing

A Co-Matching Model for Multi-choice Reading Comprehension

Shuohang Wang, Mo Yu, Shiyu Chang, Jing Jiang

ACL'18: Annual Meeting of the Association for Computational Linguistics

Image Super-Resolution via Dual-State Recurrent Networks

Wei Han☆ ‡, Shiyu Chang, Ding Liu, Mo Yu, Michael Witbrock, Thomas S. Huang

CVPR'18: IEEE Computer Vision and Pattern Recognition

Dilated Recurrent Neural Networks

Shiyu Chang, Yang Zhang, Wei Han, Mo Yu, Xiaoxiao Guo, Wei Tan, Xiaodong Cui, Michael Witbrock, Mark A. Hasegawa-Johnson, Thomas S. Huang

NIPS'17: Advances in Neural Information Processing Systems

Streaming Recommender Systems

Shiyu Chang, Yang Zhang, Jiliang Tang, Dawei Yin, Yi Chang, Mark A. Hasegawa-Johnson, Thomas S. Huang

WWW'17: ACM International World Wide Web Conference

Positive-Unlabeled Learning in Streaming Networks

Shiyu Chang, Yang Zhang, Jiliang Tang, Dawei Yin, Yi Chang, Mark A. Hasegawa-Johnson, Thomas S. Huang

KDD'16: ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Studying Very Low Resolution Recognition Using Deep Networks

Zhangyang Wang, Shiyu Chang, Yingzhen Yang, Ding Liu, Thomas S. Huang

CVPR'16: IEEE Computer Vision and Pattern Recognition

Heterogeneous Network Embedding via Deep Architectures

Shiyu Chang, Wei Han, Jiliang Tang, Guo-Jun Qi, Charu C. Aggarwal, Thomas S. Huang

KDD'15: ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Negative Link Prediction in Social Media

Jiliang Tang, Shiyu Chang, Charu C. Aggarwal, Huan Liu

WSDM'15: ACM International Conference on Web Search and Data Mining

Factorized Similarity Learning in Networks

Shiyu Chang, Guo-Jun Qi, Charu C. Aggarwal, Jiayu Zhou, Meng Wang, Thomas S. Huang

ICDM'14: IEEE International Conference on Data Mining

Learning Locally-Adaptive Decision Functions for Person Verification

Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith

CVPR'13: IEEE Computer Vision and Pattern Recognition

Vitæ

Misc

- Some words keep me moving forward:

"A job well done is its own reward. You take pride in the things you do, not for others to see, not for the respect, or glory, or any other rewards it might bring. You take pride in what you do, because you're doing your best. If you believe in something, you stick with it. When things get difficult, you try harder."

This website was built with jekyll based on a template by Martin Saveski. Some layouts are inspired by the design of David Alvarez-Melis and Jiayu Zhou.