I am a tenure-track assistant professor of Computer Science and UMIACS at University of Maryland, College Park. My research interests are in machine learning, optimization, and natural language processing. I have published ~80 papers at NeurIPS, ICML, ICLR, AISTATS, ACL, EMNLP, NAACL, COLING, CVPR, KDD, ICDM, AAAI, IJCAI, ISIT, Machine Learning (Springer), IEEE TIP/TNNLS/TKDE, etc. I am the recipient of the Best Student Paper Award at ICDM 2013 and the 2020 IEEE TCSC Most Influential Paper Award.
My recent works study how, why, and when to translate human learning strategies (e.g., curriculum, retention, sub-tasking, curiosity, exemplar learning, collaborative learning, etc.) to improve machine learning in the wild (e.g., with unlabeled, biased, noisy, redundant or distributed data, extrapolation to unseen tasks/environments). Our works are built upon empirical/theoretical analysis to the learning dynamics of neural networks and tools from discrete and continuous optimization. Our goal is to develop efficient, versatile, trustworthy, and environmentally-friendly hybrid-intelligence based on coevolution between human and machine. A list of my research topics can be found below.
I was a visiting research scientist at Google between 2021-2022. Before that, I was a Ph.D. student in Computer Science at University of Washington and a member of MELODI lab led by Prof. Jeff A. Bilmes. I have been a research assistant at University of Technology, Sydney (UTS) and Nanyang Technological University (NTU), supervised by Prof. Dacheng Tao (University of Sydney). I was a research intern at Yahoo! Labs, supervised by Hua Ouyang (Apple) and Yi Chang (Jilin University), and a research intern at Microsoft Research, supervised by Lin Xiao (Facebook AI Research). I also work closely with several members and students of Australian AI Institute.
- 2022/12: I will teach CMSC-828A on “Fantastic Machine Learning Paradigms and Where to use Them” in Spring 2023.
- 2022/12: I will serve as an SPC (meta-reviewer) for IJCAI 2023.
- 2022/11: One XAI paper on extracting local reasoning chains for subtasks from neural networks such as ResNet and ViT has been accepted by TMLR.
- 2022/10: One paper (adversarial attacks to Question-Answer models) has been accepted by EMNLP 2022.
- 2022/09: Three papers (adversarial augmentation for continual learning, adversarial augmentation for representation learning, federated learning from pre-trained models) have been accepted by NeurIPS 2022.
- 2022/06: I will serve as an Area Chair for Winter Conference on Applications of Computer Vision (WACV) 2023.
- 2022/05: Two papers about environment-and-task-curriculum for RL and adversarial augmentation for self-supervised learning have been accpeted by ICML 2022.
- 2022/04: One paper about personalized federated learning has been accpeted by IJCAI 2022 as a long presentation.
- 2022/04: One paper of phrase-level textual adversarial attack with label preservation has been accpeted by NAACL 2022 Findings.
- 2022/03: One paper (Learning to Collaborate in Decentralized Learning of Personalized Models) has been accepted by CVPR 2022.
- 2022/02: One paper (Token Dropping for Efficient BERT Pretraining) has been accepted by ACL 2022.
- 2022/01: Three papers (Pareto Policy Pool for Model-based Offline RL, Diverse Client Selection for Federated Learning, Omni-scale CNNs for Time Series) have been accepted by ICLR 2022.
- 2021/12: One paper of Federated Prototype Learning has been accepted to AAAI 2022.
- 2021/11: I will serve as an SPC for SIGKDD 2022.
- 2021/09: Three papers (1 spotlight for Submodular Partitioning, Curriculum RL and Planning, Class-Disentanglement) have been accepted to NeurIPS 2021. Congratulations to Shuang Ao and Kaiwen Yang for their first paper!
- 2021/09: One paper of sentiment bias has been accepted to EMNLP 2021 (findings).
- 2021/08: I will serve as an SPC for AAAI 2022.
- 2021/02: I am selected as an expert reviewer for ICML 2021.
- 2021/01: One paper of curriculum learning and training dynamics has been accepted to AISTATS 2021.
- 2021/01: Three papers (RoCL for curriculum noisy-label learning, AutoLRS for auto-learning rate schedule, IPN for prototype zero-shot learning) have been accepted to ICLR 2021.
- 2021/01: One paper of knowledge graph completion has been accepted to WWW 2021.
- 2020/10: Selected among the top 10% of high-scoring reviewers for NeurIPS 2020.
- 2020/09: One paper of curriculum learning and training dynamics has been accepted to NeurIPS 2020.
- 2020/06: One paper of curriculum semi/self-supervised learning has been accepted to ICML 2020.
- Machine Learning (2008-present)
- Curriculum Learning (for 2-6 below, using tools in 7-8)
- Self-supervised/Semi-supervised Learning
- Reinforcement Learning
- Collaborative Learning on graphs/networks, Ensemble Method
- Robust Learning on Noisy Data
- Meta-Learning, Few-shot/Zero-shot Learning
- Training Dynamics and Geometry of Neural Networks
- Continuous-discrete Optimization, Submodular Optimization
- Spectral Method for Matrix Factorization and Graphical Models
- Matrix and Tensor Factorization: Low-rank Approximation, Completion, Robust PCA, NMF
- Compressed Sensing (1-bit and k-bit measurements), Sparse Learning
- Dimension Reduction, Manifold Learning
- Natural Language Processing (2016-present)