Huaxiu Yao (姚骅修)
Bio
Currently, I am a Postdoctoral Scholar at IRIS Lab, Department of Computer Science, Stanford University hosted by Prof. Chelsea Finn. I am also affiliated with Stanford AI Lab, CRFM, and ML Group. I received my Ph.D. degree at Pennsylvania State University under the advisory of Prof. Zhenhui (Jessie) Li. During my Ph.D. study, I also spent time visiting SAILING Lab, CMU hosted by Prof. Eric P. Xing. Earlier, I got my B.Eng. degree from the University of Electronic Science and Technology of China under the advisory of Prof. Defu Lian (now in USTC) and Prof. Tao Zhou.
My current research focuses on building machine learning models that are robust to distribution shifts. I am also passionate about applying these methods to solve real-world problems with limited data. Revolving around this goal, I mainly study the following topics:
- Machine Learning: meta/multi-task/continual learning, out-of-distribution robustness, self-supervised learning, federated learning
- Applications: ai for science (e.g., biology, chemistry), ai for social good (e.g., education, transportation), language modeling
News
[2022.05] One paper was accepted by ICML 2022
[2022.03] We will organize the First Workshop on Pre-training at ICML 2022. Stay tuned!
[2022.02] One paper was accepted by ACL 2022
[2022.01] One paper was accepted by ICLR 2022
[2021.09] Two papers were accepted by NeurIPS 2021
[2021.08] One paper was accepted by EMNLP 2021
[2021.05] One paper was accepted by ICML 2021
[2021.04] Join Stanford University as a Postdoctoral Scholar hosted by Prof. Chelsea Finn
[2020.09] Remotely visit SAILING Lab hosted by Prof. Eric P. Xing starting from fall 2020
publicationS
Preprint
[1] Yoonho Lee, Huaxiu Yao, Chelsea Finn, Diversify and Disambiguate: Learning From Underspecified Data, arXiv 2202.03418. [Project Page] [arXiv]
[2] Ying Wei, Peilin Zhao, Huaxiu Yao, Junzhou Huang, Transferable Neural Processes for Hyperparameter Optimization, arXiv 1909.03209 (the short version is published in NeurIPS 2019 Workshop on Meta-Learning). [arXiv]
[3] Ali Ghadirzadeh, Petra Poklukar, Xi Chen, Huaxiu Yao, Hossein Azizpour, Mårten Björkman, Chelsea Finn, Danica Kragic, Few-Shot Learning With Weak Supervision, ICLR 2021 Workshop on Learning to Learn. [Openreview] [Poster]
2022
[1] Huaxiu Yao*, Yu Wang*, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn, Improving Out-of-Distribution Robustness via Selective Augmentation, in Proceeding of the Thirty-ninth International Conference on Machine Learning (ICML 2022), Baltimore, MD, July 2022. [arXiv] [Code]
[2] Huaxiu Yao, Linjun Zhang, Chelsea Finn, Meta-Learning with Fewer Tasks through Task Interpolation, in Proceeding of the 10th International Conference on Learning Representations (ICLR 2022), Virtual, Apr. 2022 (Oral, 54/3391). [Openreview] [PDF] [Code] [Slides] [Poster] [arXiv]
[3] Yingxiu Zhao, Zhiliang Tian, Huaxiu Yao, Yinhe Zheng, Dongkyu Lee, Yiping Song, Jian Sun, Nevin Zhang, Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation, in Proceeding of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), Dublin, Ireland, May 2022 (long paper). [Openreview] [PDF] [arXiv]
[4] Yinjie Jiang, Yemin Yu, Ming Kong, Yu Mei, Luotian Yuan, Zhengxing Huang, Kun Kuang, Zhihua Wang, Huaxiu Yao, James Zou, Connor W. Coley, Ying Wei, Artificial Intelligence for Retrosynthesis Prediction, Engineering (Engineering), 2022 (survey).
2021
[5] Huaxiu Yao*, Yu Wang*, Ying Wei, Peilin Zhao, Mehrdad Mahdavi, Defu Lian, Chelsea Finn, Meta-learning with an Adaptive Task Scheduler, in Proceeding of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021), Virtual, Dec. 2021. [PDF] [Supplementary] [Code] [Slides] [Poster] [arXiv]
[6] Huaxiu Yao, Ying Wei, Longkai Huang, Ding Xue, Junzhou Huang, Zhenhui Li, Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery, in Proceeding of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021), Virtual, Dec. 2021. [PDF] [Supplementary] [Code] [Slides]
[7] Huaxiu Yao, Yingxin Wu, Maruan Al-Shedivat, Eric P. Xing, Knowledge-Aware Meta-learning for Low-Resource Text Classification, in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), Punta Cana, Dominican Republic, Nov. 2021 (Short Paper, Oral). [PDF] [Code] [Slides] [Poster] [arXiv]
[8] Huaxiu Yao*, Longkai Huang*, Linjun Zhang, Ying Wei, Li Tian, James Zou, Junzhou Huang, Zhenhui Li, Improving Generalization in Meta-learning via Task Augmentation, in Proceeding of the Thirty-eighth International Conference on Machine Learning (ICML 2021), Virtual, Jul. 2021. [PDF] [Supplementary] [Code] [Slides] [Poster] [arXiv]
[9] Jiatu Shi*, Huaxiu Yao*, Xian Wu, Tong Li, Zedong Lin, Tengfei Wang, Binqiang Zhao, Relation-aware Meta-learning for E-commerce Market Segment Demand Prediction with Limited Records, in Proceeding of the 14th ACM International Conference on Web Search and Data Mining (WSDM 2021), Virtual, Mar. 2021. [PDF] [arXiv]
[10] Porter Jenkins, Ahmad Farag, Stockton Jenkins, Huaxiu Yao, Suhang Wang, Zhenhui Li, Neural Utility Functions, in Proceeding of the Thirty-fifth AAAI Conference on Artificial Intelligence (AAAI 2021), Virtual, Feb. 2021. [PDF]
[11] Chuxu Zhang, Huaxiu Yao, Lu Yu, Chao Huang, Dongjing Song, Haifeng Chen, Meng Jiang, Nitesh V. Chawla, Inductive Contextual Relation Learning for Personalization, ACM Transactions on Information System (TOIS) 39, no. 3 (2021): 1-22. [PDF]
2020
[12] Huaxiu Yao, Yingbo Zhou, Mehrdad Mahdavi, Zhenhui Li, Richard Socher, Caiming Xiong, Online Structured Meta-learning, in Proceeding of the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020), Virtual, Dec. 2020. [PDF] [Supplementary] [Code] [Slides] [Poster] [arXiv]
[13] Huaxiu Yao, Xian Wu, Zhiqiang Tao, Yaliang Li, Bolin Ding, Ruirui Li, Zhenhui Li, Automated Relational Meta-learning, in Proceeding of the Eighth International Conference on Learning Representations (ICLR 2020), Virtual, Apr. 2020. [Openreview] [PDF] [Code] [Slides] [arXiv]
[14] Huaxiu Yao, Chuxu Zhang, Ying Wei, Meng Jiang, Suhang Wang, Junzhou Huang, Nitesh V. Chawla, Zhenhui Li, Graph Few-shot Learning via Knowledge Transfer, in Proceeding of the Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI 2020), New York, NY, Feb. 2020 (the short version is published in NeurIPS 2019 Graph Representation Learning Workshop). [PDF] [Full Paper] [Code] [arXiv]
[15] Chuxu Zhang, Huaxiu Yao, Chao Huang, Meng Jiang, Zhenhui Li, Nitesh V. Chawla, Few-Shot Knowledge Graph Completion, in Proceeding of the Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI 2020), New York, NY, Feb. 2020. [PDF] [Code] [Poster] [arXiv]
[16] Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Charu Aggarwal, Prasenjit Mitra, Suhang Wang, Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values, in Proceeding of the Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI 2020), New York, NY, Feb. 2020. [PDF] [arXiv]
[17] Xinshi Zang, Huaxiu Yao, Guanjie Zheng, Nan Xu, Kai Xu, Zhenhui Li, MetaLight: Value-based Meta-reinforcement Learning for Online Universal Traffic Signal Control, in Proceeding of the Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI 2020), New York, NY, Feb. 2020. [PDF] [Code] [Poster]
[18] Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Yiqi Wang, Jiliang Tang, Charu Aggarwal, Prasenjit Mitra, Suhang Wang, Investigating and Mitigating Degree-Related Biases in Graph Convolutional Networks, in Proceeding of the 29th ACM International Conference on Information and Knowledge Management (CIKM 2020), Galway, Ireland, Oct. 2020. [PDF] [arXiv]
[19] Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, Suhang Wang, Transferring Robustness for Graph Neural Network Against Poisoning Attacks, in Proceeding of the 13th ACM International Conference on Web Search and Data Mining (WSDM 2020), Houston, TX, Feb. 2020. [PDF] [Code] [arXiv]
2019
[20] Huaxiu Yao, Ying Wei, Junzhou Huang, Zhenhui Li, Hierarchically Structured Meta-learning, in Proceeding of the 36th International Conference on Machine Learning (ICML 2019), Long Beach, CA, June 2019. [PDF] [Supplementary] [Slides] [Poster] [Code] [arXiv]
[21] Huaxiu Yao, Yiding Liu, Ying Wei, Xianfeng Tang, Zhenhui Li, Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction, in Proceeding of The Web Conference 2019 (WWW 2019), San Francisco, CA, May 2019 (Research Track, Long Paper). [PDF] [Slides] [Poster] [Code] [arXiv with Erratum]
[22] Xianfeng Tang, Boqing Gong, Yanwei Yu, Huaxiu Yao, Yandong Li, Haiyong Xie, Xiaoyu Wang, Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference, in Proceeding of The Web Conference 2019 (WWW 2019), San Francisco, CA, May 2019 (Research Track, Long Paper). [PDF] [arXiv]
[23] Huaxiu Yao*, Xianfeng Tang*, Hua Wei, Guanjie Zheng, Zhenhui Li, Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction, in Proceeding of the Thirty-third AAAI Conference on Artificial Intelligence (AAAI 2019), Honolulu, Hawaii, Jan. 2019. [PDF] [Poster] [Code] [Spotlight] [arXiv]
[24] Huaxiu Yao, Defu Lian, Yi Cao, Yifan Wu, Tao Zhou, Predicting Academic Performance for College Students: A Campus Behavior Perspective, ACM Transactions on Intelligent Systems and Technology (TIST) 10.3 (2019): 24. [PDF] [arXiv]
2018
[25] Huaxiu Yao, Fei Wu, Jintao Ke, Xianfeng Tang, Yitian Jia, Siyu Lu, Pinghua Gong, Jieping Ye, Zhenhui Li, Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction, in Proceeding of the Thirty-second AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, LA, Feb. 2018. [PDF] [Poster] [Code] [Spotlight] [Penn State News] [arXiv]
[26] Hua Wei*, Guanjie Zheng*, Huaxiu Yao, and Zhenhui Li, IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control, in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2018), London, UK, Aug. 2018 (Research Track). [PDF] [Code] [Demo]
[27] Yi Cao*, Jian Gao*, Defu Lian, Zhihai Rong, Jiatu Shi, Qing Wang, Yifan Wu*, Huaxiu Yao*, Tao Zhou*. Orderliness predicts academic performance: behavioural analysis on campus lifestyle, Journal of the Royal Society Interface (J. R. Soc. Interface), 15 (146), (2018) 20180210 (alphabetical order). [PDF] [Supplementary]
Teaching & mentoring
Teaching Experience
Guest Lecture
Teaching Assistant at Penn State
Mentored Students
[2022 - now] Caroline Choi, undergrad@Stanford
[2022 - now] Nathan Hu, undergrad@Stanford
[2022 - now] Yiping Wang, undergrad@ZJU
[2022 - now] Xinyu Yang, undergrad@SJTU
[2022 - now] Zhiyu Xie, undergrad@THU
[2021 - 2022] Yingxiu Zhao, Ph.D. student@HKUST, Achievement: ACL'22
[2021 - 2022] Yingxin Wu, undergrad@USTC -> Ph.D. student@Stanford, Achievement: EMNLP'21
[2021 - 2022] Yu Wang, undergrad@USTC -> Ph.D. student@UCSD, Achievements: NeurIPS'21, ICML'22
[2021 - now] Takao Yatagai, undergrad@Stanford
[2021 - now] Govind Chada, undergrad@Stanford
[2019] Xinshi Zang, undergrad@SJTU -> Ph.D. student@CUHK, Achievement: AAAI'20
Services
Workshop & Tutorial Organizer
Workshop
Tutorial
Program Committee Member/Reviewer
Conference Program Committee Member/Reviewer:
Journal Invited Reviewer:
miscellaneous
Invited Talks
Actionable Machine Learning for Tackling Distribution Shift
Improving Generalization in Meta-learning through Organization and Augmentation
Improving Generalization in Low-resource molecular modeling through organization and augmentation
Learning to Learn with Structured Knowledge
Honors and Awards
Industry Internships
contact
Office: 322, Gates Building, Stanford, CA 94085
Copyright 2019