Chao Zhang

My research aims to design machine learning and data-driven models to solve practical and challenging problems in science and engineering. I am particularly interested in the following topics:

• Learning from limited supervision: weak supervision, self supervision, unsupervised learning
• Uncertainty in ML: uncertainty quantification, active learning, decision making under uncertainty
• Spatiotemporal modeling: spatial graphs, time series, dynamics, 3D molecular data
• Generation and inverse design: learning for optimization, generative models, network design
• Knowledge extraction and NLP: information extraction, multi-modal extraction, LM pre-training & fine-tuning

On the data side, I work a lot with spatiotemporal data, text data, and graph data. On the application side, I am passionate about interdisciplinary research and enjoy developing data-driven solutions to accelerate scientific discovery through close collaboration with domain experts. The techniques I develop are motivated by applications in material science, biomedical science, transportation, and public health.

Acknowledgment: My work has been generously supported by research funding/gift from NSF (IIS CAREER-2144338, IIS-2106961, IIS-2008334), ONR MURI , Kolon, HomeDepot, and Adobe. My work has also been recognized by an NSF CAREER Award, a Facebook Faculty Award, an Amazon AWS Machine Learning Research Award, a Google Faculty Research Award, a Kolon Faculty Fellowship, an ACM SIGKDD Dissertation Runner-up Award, and several paper awards from IMWUT (UbiComp), ECML/PKDD, and ML4H.

Below are the main research projects at my group and some recent representative works:

• Learning with limited supervision: The lack of training data is a major bottleneck for training deep learning models. Our recent works approach this challenge by:
  • Fine-tuning pre-trained models with weak supervision:
    • Fine-Tuning Pre-trained Language Model with Weak Supervision, NAACL 2021
    • Text Classification Using Label Names Only: A Language Model Self-Training Approach, EMNLP 2020
    • Weakly-Supervised Neural Text Classification, CIKM 2018
  • Interactive weakly-supervised learning to close the gap between weak & full supervision:
    • AcTune: Uncertainty-Aware Active Self-Training for Active Fine-Tuning of Language Models, NAACL 2022
    • PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning, ACL 2022
• Uncertainty quantification & exploitation: Uncertainty-aware ML models are key elements to trustworthy AI systems. Unfortunately, many deep learning models produce uncertainty-agnostic point estimates or miscalibrated distributions. We develop techniques to quantify uncertainty for deep learning and exploit uncertainty for downstream decision making:
  • Uncertainty quantification:
    • When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting, NeurIPS 2021
    • SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates, ICML 2020
    • Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data, EMNLP 2020
    • RDeepSense: Reliable Deep Mobile Computing Models with Uncertainty Estimations, UbiComp 2018
  • Uncertainty exploitation:
    • End-to-end Stochastic Programming with Energy-based Model, NeurIPS 2022
• Spatiotemporal dynamics modeling: Space and time are two most important dimensions in many science and engineering applications. We develop deep learning models that can model and predict the dynamics of spatial systems, at both macro-level (e.g., transportation, epidemiology) and micro-level (e.g., molecular dynamics).
  • Spatiotemporal graphs:
    • T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction, IEEE ITS 2020
    • Regions, Periods, Activities: Uncovering Urban Dynamics via Cross-Modal Representation Learning, WWW 2017
  • Time series modeling:
    • CAMUL: Calibrated and Accurate Multi-view Time-Series Forecasting, WWW 2022
    • When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting, NeurIPS 2021
    • DeepMove: Predicting Human Mobility with Attentional Recurrent Networks, WWW 2018
• Generation and inverse design: We study how to guide deep generative models to design samples that satisfy pre-determined properties.
  • End-to-end Stochastic Programming with Energy-based Model, NeurIPS 2022
  • Transformer-Based Neural Text Generation with Syntactic Guidance, preprint
  • A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization, ICML 2019
• Knowledge extraction and NLP: We design ML models that can automatically extract information about entities, relations, taxonomies, and events from massive unstructured data (e.g., scientific literature). We focus on tackling the challenges of low-resource information extraction and multi-modal information extraction.
  • Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition, KDD 2022
  • BERTifying Hidden Markov Models for Multi-Source Weakly Supervised Named Entity Recognition, ACL 2021
  • BOND: Bert-Assisted Open-Domain Named Entity Recognition with Distant Supervision, KDD 2020
  • STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths, KDD 2020
  • TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering, KDD 2018

(* denotes equal contribution)

• 2022 ML4H Outstanding Paper Award
• 2022 NSF Career Award
• 2021 Facebook Faculty Research Award
• 2021 Kolon Faculty Fellowship
• 2020 Amazon AWS Machine Learning Research Award
• 2020 Google Faculty Research Award
• 2019 ACM SIGKDD Dissertation Award Runner-up
• 2018 ACM IMWUT Distinguished Paper Award
• 2015 ECML/PKDD Best Student Paper Runner-up Award
• 2013 Chiang Chen Overseas Graduate Fellowship

• SDE-Net: Efficient uncertainty estimation for deep neural networks
• CHMM: BERT-conditional hidden Markov model for multi-source weakly-supervised learning
• COSINE: Language model fine-tuning with weak supervision
• BOND: Distantly-supervised named entity recognition
• STEAM: Automatic taxonomy expansion
• TaxoGen: Unsupervised topic taxonomy construction from text corpus
• WestClass: Weakly-supervised text classification
• GeoBurst: Unsupervised spatiotemporal event detection

• 2023 Spring: CX4240: Introduction to Computational Data Analysis
• 2022 Spring: CX4240: Introduction to Computational Data Analysis
• 2021 Fall: CSE8803-DLT: Deep Learning for Text Data
• 2021 Spring: CX4240: Introduction to Computational Data Analysis
• 2020 Fall: CSE8803-DLT: Deep Learning for Text Data
• 2020 Spring: CX4240: Introduction to Computational Data Analysis
• 2019 Fall: CSE8803-DLT: Deep Learning for Text Data
• 2019 Spring: CX4240: Introduction to Computational Data Analysis

Prospective students: I am always looking for strong and motivated students to join our group. If you are interested in working with me, you can either email me or fill out this form.

Current:

• Rui Feng: Ph.D. Student in CS
• Lingkai Kong: Ph.D. Student in CSE
• Yinghao Li: Ph.D. Student in ML
• Haorui Wang: Ph.D. Student in CSE
• Kuan Wang: Ph.D. Student in CSE
• Yue Yu: Ph.D. Student in CSE
• Rongzhi Zhang: Ph.D. Student in ML
• Yuchen Zhuang: Ph.D. Student in ML
• Binghong Chen: Ph.D. Student in CSE (co-advised with Prof. Le Song)
• Pranav Shetty: Ph.D. Student in ML (JP Morgan AI Ph.D. Fellowship, co-advised with Prof. Rampi Ramprasad)
• Yanbo Xu: Ph.D. Student in ML (co-advised with Prof. Alexey Tumanov)
• Vidit Jain: M.S. Student in CS
• Mukund Rungta: M.S. Student in CS
• Junyang Zhang: B.S. Student in CS

Alumni:

• Piyush Patil: M.S. Student in CS
• Mengyang Liu: M.S. Student in CSE
• Isaac Rehg: M.S. in CS
• Wendi Ren: M.S. in CSE
• Ruijia Wang: M.S. in CSE
• Yi Rong: Visiting Ph.D. Student