Short Bio
Yao-Yuan is currently working in DeepMind. He received his Ph.D. in 2022 from the Computer Science and Engineering department of UCSD, advised by Professor Kamalika Chaudhuri. His thesis was on trustworthy machine learning, which includes topics such as adversarial examples, interpretability, and spurious correlations. Prior to joining UCSD, he received his B.S. in Computer Science from National Taiwan University in 2016.
Here are my CV, research statement, and three representative papers (paper1, paper2, paper3).
Here are some problems he previously worked on:
- Cost-sensitive multi-label classification
- Active learning
- Brain decoding with electroencephalogram (EEG)
News
- Our work "Person-identifying brainprints are stably embedded in EEG mindprints" get accepted to Scientific Reports
- Our work "What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning" get accepted to NeurIPS 2022
- Our work "Connecting Interpretability and Robustness in Decision Trees through Separation" get accepted to ICML 2021
- Our work "A Closer Look at Accuracy vs. Robustness" get accepted to NeurIPS 2020
- Our work "Robustness for Non-Parametric Methods: A Generic Attack and Defense" get accepted to AISTATS 2020
- I am presenting my work at the Machine Learning with Guarantees workshop at NeurIPS 2019
- I am presenting my work at ACML 2019
Experiences
- Research Engineer, DeepMind, August 2022 - Current
- Ph.D., Computer Science and Engineering, University of California, San Diego, September 2017 - June 2022
- Alternative service of education, Minister of Education, Aug 2016 - June 2017
- B.S., Department of Computer Science and Information Engineering, National Taiwan University, September 2012 - June 2016
- Lab member, Modeling & Informatics Lab, 2014 - 2016
- Research Assistant, Computational Learning Lab, 2013 - 2016
- Lab member,Fast Crypto Lab, 2012 - 2014
Publications
Preprints
-
Understanding Rare Spurious Correlations in Neural Networks
Yao-Yuan Yang, Chi-Ning Chou, and Kamalika Chaudhuri, in submission, 2022, [bib] [arxiv] [code]
-
libact: Pool-based Active Learning in Python
Yao-Yuan Yang, Shao-Chuan Lee, Yu-An Chung, Tung-En Wu, Si-An Chen, and Hsuan-Tien Lin, 2017, [bib] [arxiv] [code]
Postprints
-
Probing Predictions on OOD Images via Nearest Categories
Yao-Yuan Yang, Cyrus Rashtchian, Ruslan Salakhutdinov, and Kamalika Chaudhuri, in Transactions on Machine Learning Research, 2023, [bib] [arxiv] [code]
-
What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
Bogdan Kulynych*, Yao-Yuan Yang*, Yaodong Yu, Jarosław Błasiok, and Preetum Nakkiran, in NeurIPS, 2022, [bib] [arxiv] [code]
-
Person-identifying brainprints are stably embedded in EEG mindprints
Yao-Yuan Yang, Angel Hsing-Chi Hwang, Chien-Te Wu, and Tsung-Ren Huang, in Scientific Reports, 2022, [bib] [url]
-
TorchAudio: Building Blocks for Audio and Speech Processing
Yao-Yuan Yang*, Moto Hira*, Zhaoheng Ni*, Anjali Chourdia, Artyom Astafurov, Caroline Chen, Ching-Feng Yeh, Christian Puhrsch, David Pollack, Dmitriy Genzel, Donny Greenberg, Edward Z. Yang, Jason Lian, Jay Mahadeokar, Jeff Hwang, Ji Chen, Peter Goldsborough, Prabhat Roy, Sean Narenthiran, Shinji Watanabe, Soumith Chintala, Vincent Quenneville-Bélair, and Yangyang Shi, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, [bib] [arxiv] [code]
-
Hide and seek: Choices of virtual backgrounds in video chats and their effects on perception
Angel Hsing-Chi Hwang, Cheng Yao Wang, Yao-Yuan Yang, and Andrea Stevenson Won, in Proceedings of the 2021 ACM Conference on Computer Supported Cooperative Work (CSCW), 2021, [bib] [pdf] [video] [url]
-
Connecting Interpretability and Robustness in Decision Trees through Separation
Michal Moshkovitz, Yao-Yuan Yang, and Kamalika Chaudhuri, in Proceedings of International Conference on Machine Learning (ICML), 2021, [bib] [arxiv] [code]
-
A Closer Look at Accuracy vs. Robustness
Yao-Yuan Yang*, Cyrus Rashtchian*, Hongyang Zhang, Ruslan Salakhutdinov, and Kamalika Chaudhuri, in Proceedings of Neural Information Processing Systems (NeurIPS), 2020, [bib] [arxiv] [code]
-
Robustness for Non-Parametric Classification: A Generic Attack and Defense
Yao-Yuan Yang*, Cyrus Rashtchian*, Yizhen Wang, and Kamalika Chaudhuri, in Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2020, [bib] [arxiv] [code]
-
PABLO: Helping Novices Debug Python Code Through Data-Driven Fault Localization
Benjamin Cosman, Madeline Endres, Georgios Sakkas, Leon Medvinsky, Yao-Yuan Yang, Ranjit Jhala, Kamalika Chaudhuri, and Westley Weimer, in Proceedings of the Special Interest Group on Computer Science Education (SIGCSE), 2020, [bib] [pdf]
-
Deep Learning with a Rethinking Structure for Multi-label Classification
Yao-Yuan Yang, Yi-An Lin, Hong-Min Chu, and Hsuan-Tien Lin, in Proceedings of the Asian Conference on Machine Learning (ACML), 2019, [bib] [arxiv] [code]
-
Cost-Sensitive Reference Pair Encoding for Multi-Label Learning
Yao-Yuan Yang, Kuan-Hao Huang, Chih-Wei Chang, and Hsuan-Tien Lin, in Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2018, [bib] [arxiv] [pdf] [code]