Chao Zhang

I am broadly interested in developing intelligent systems that can facilitate data-driven task support and decision making. I am recently focusing on applying machine learning to analyze massive data (text, graphs, spatiotemporal data) to accelerate scientific discovery, especially for material science and biomedical applications. Below are some research problems I am working on:

• Knowledge extraction and text mining: Extract information about entities, relations, taxonomies, and events from unstructured data such as Web data and scientific literature. We are tackling challenges for low-resource information extraction and multi-modal information extraction:
  • 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
  • TrioVecEvent: Embedding-Based Online Local Event Detection in Geo-Tagged Tweet Streams, KDD 2017
  • GeoBurst: Real-Time Local Event Detection in Geo-Tagged Tweet Streams, SIGIR 2016
• Learning predictive models from limited data: The lack of labeled training data is a major bottleneck for training deep predictive models. We learn deep learning predictive models from a small amount of labeled data, or just using weakly labeled data derived from domain knowledge. Our recent works combine self-supervised learning with self-training as a generic approach to learning from limited supervision.
  • Text Classification Using Label Names Only: A Language Model Self-Training Approach, EMNLP 2020
  • Denoising Multi-Source Weak Supervision for Neural Text Classification, EMNLP 2020
  • SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup, EMNLP 2020
  • Weakly-Supervised Neural Text Classification, CIKM 2018
• Uncertainty estimation and out-of-distribution robustness: Current deep learning models typically assume the training and test distributions are i.i.d., which is rarely the case in practice. As a result, deep learning models can fail miserably in open-world settings. We want machines to go beyond the training distribution: How can we quantify uncertainties for deep learning models and enable them say "I don't know" for out-of-distribution samples? How can we make them to generalize to different domains and make robust predictions? How can we make them fast adapt to tasks that were never seen before?
  • 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
• Guided Generative Models: We study how to guide deep generative models with pre-conditions, to generate samples that satisfy desired properties.
  • Transformer-Based Neural Text Generation with Syntactic Guidance , preprint
  • A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization, ICML 2019
• Spatiotemporal data mining: I have also worked on spatiotemporal data mining, along two lines: 1) Deep learning for predictive spatiotemporal data analytics; 2) Multi-modal spatiotemporal analytics for semantics-rich spatiotemporal understanding:
  • Computing Trajectory Similarity in Linear Time: A Generic Seed-Guided Neural Metric Learning Approach, ICDE 2019
  • DeepMove: Predicting Human Mobility with Attentional Recurrent Networks, WWW 2018
  • Regions, Periods, Activities: Uncovering Urban Dynamics via Cross-Modal Representation Learning, WWW 2017
  • GMove: Group-Level Mobility Modeling Using Geo-Tagged Social Media, KDD 2016

• We have 4 paper accepted by EMNLP'20, discussing model calibration, sequence labeling, and zero-shot text classification.
• We have 1 paper accepted by ICML'20. We introduce a new method for quantifying uncertainties for neural networks based on the connection between NN and linear systems.
• We have 4 papers accepted by KDD'20, discussing self-supervised taxonomy construction, low-resource NER, hierarchical topic mining, and tensor factorization.
• Congrats to my student Wendi Ren for winning the Marshall D. Williamson Fellowship!
• Honored to receive the 2020 Google Faculty Research Award!
• Two papers accepted by the Web Conference 2020.
• Honored to receive the ACM SIGKDD 2019 Dissertation Runner-up Award!
• Our monograph Multidimensional Mining of Massive Text Data is published by Morgan & Claypool!

• 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

(* denotes equal contribution)

• SDE-Net: Efficient uncertainty estimation for deep neural networks
• 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 from social media streams

• 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

• Ph.D. Students:
  • Lingkai Kong
  • Rui Feng
  • Yue Yu
  • Yinghao Li
• Master Students:
  • Rongzhi Zhang
  • Yuchen Zhuang
  • Isaac Rehg
  • Ruijia Wang
• Alumni:
  • Wendi Ren
  • Yi Rong