Yao-Hung Hubert Tsai

⚔ About Me ⚔

I am a second-year Ph.D. student in Machine Learning Department at Carnegie Mellon University under the supervision of Dr. Ruslan Salakhutdinov and Dr. Louis-Philippe Morency. My research interests lie in Deep Learning and its applications, especially on Multi-Modal Learning, Transfer Learning, and Generative Learning.

When I was not around CMU, I did the internship at Microsoft Research/ Allen Institute for Artificial Intelligence (AI2) and visited Kokuritsu Kenkyū Kaihatsu Hōjin Rikagaku Kenkyūjyo (RIKEN).

Here is my Google Scholar/ LinkedIn/ GitHub/ CV (last updated in 06/20/2018).

-- contact me: yaohungt [at] cs.cmu.edu

♛ Selected Research during Ph.D. ♛

★ Multimodal Learning ★

Multimodal Co-Learning
Yao-Hung Hubert Tsai et al.
arXiv: 2018
[coming soon]
Learning Factorized Multimodal Representations
Yao-Hung Hubert Tsai*, Paul Pu Liang*, Amir Zadeh, Louis-Philippe Morency and Ruslan Salakhutdinov (*equal contribution)
arXiv:1806.06176 2018
Improving One-Shot Learning through Fusing Side Information
Yao-Hung Hubert Tsai and Ruslan Salakhutdinov
NIPS Learning with Limited Labeled Data: Weak Supervision and Beyond (NIPS LLD) 2017
Bay Area Machine Learning Symposium (BayLearn) 2017 (best poster)
Learning Robust Visual-Semantic Embeddings
Yao-Hung Hubert Tsai, Liang-Kang Huang and Ruslan Salakhutdinov
International Conference on Computer Vision (ICCV) 2017

★ General Topics in Deep Learning ★

Approximate Empirical Bayes for Deep Neural Networks
Yao-Hung Hubert Tsai*, Han Zhao*, Ruslan Salakhutdinov and Geoff Gordon (*equal contribution)
UAI Workshop on Uncertainty in Deep Learning (UAI Workshop) 2018
[coming soon]
Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
Makoto Yamada*, Denny Wu*, Yao-Hung Hubert Tsai, Ichiro Takeuchi, Ruslan Salakhutdinov and Kenji Fukumizu (*equal contribution)
arXiv:1802.06226 2018
Selecting the Best in GANs Family: a Post Selection Inference Framework
Yao-Hung Hubert Tsai*, Makoto Yamada*, Denny Wu*, Ruslan Salakhutdinov, Ichiro Takeuchi and Kenji Fukumizu (*equal contribution)
International Conference on Representation Learning Workshop (ICLR Workshop) 2018
"Dependency Bottleneck" in Auto-encoding Architectures: an Empirical Study
Yao-Hung Hubert Tsai*, Denny Wu*, Yixiu Zhao*, Makoto Yamada and Ruslan Salakhutdinov (*equal contribution)
arXiv:1802.05408 2018
Discovering Order in Unordered Datasets: Generative Markov Networks
Yao-Hung Hubert Tsai, Han Zhao, Ruslan Salakhutdinov and Nebojsa Jojic
Neural Information Processing Systems Time Series Workshop (NIPS TSW) 2017 (oral)

♛ Selected Research before Ph.D. ♛

★ Domain Adaptation ★

Transfer Neural Trees for Heterogeneous Domain Adaptation
Wei-Yu Chen, Tzu-Ming Harry Hsu, Yao-Hung Hubert Tsai, Yu-Chiang Frank Wang and Ming-Syan Chen
European Conference on Computer Vision (ECCV) 2016
[PDF] [Poster]
Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation
Yao-Hung Hubert Tsai, Yi-Ren Yeh and Yu-Chiang Frank Wang
Computer Vision and Pattern Recognition (CVPR) 2016
[PDF] [Supplementary] [Poster] [Code]
Domain-Constraint Transfer Coding for Imbalanced Unsupervised Domain Adaptation
Yao-Hung Hubert Tsai, Cheng-An Hou, Wei-Yu Chen, Yi-Ren Yeh and Yu-Chiang Frank Wang
Association for the Advancement of Artificial Intelligence (AAAI) 2016
Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data
Tzu-Ming Harry Hsu, Wei-Yu Chen, Cheng-An Hou, Yao-Hung Hubert Tsai, Yi-Ren Yeh and Yu-Chiang Frank Wang
International Conference on Computer Vision (ICCV) 2015