I am a Ph.D. student in the Computer Science and Engineering Department, University of Connecticut. My advisor is Prof. Jinbo Bi. I was supervised by Prof. Fei Wang and had the opportunity to work with Prof. Viktor K. Prasanna, Dr. Jing Huang and Dr. Jie Chen. Before I came here, I got my M.S. degree at Beijing University of Posts and Telecommunications (BUPT). I have spent some time interning in University of Southern California (2014), Chinese Academic of Science (2015), JD AI Research (2018), IBM Thomas J. Watson Research Center (2019) and MIT-IBM Watson AI Lab (2020).
My primary research interests are in deep graph learning and machine learning using large-scale datasets, with an emphasis on healthcare informatics, knowledge graphs, cheminformatics and bioinformatics.
01/2020 - Present | Research Intern | MIT-IBM Watson AI Lab, IBM Research
- Deep Graph Structure Learning.
05/2019 - 09/2019 | Research Intern | IBM Thomas J. Watson Research Center, IBM Research
- Developed machine learning methods for knowledge induction in deep domains involving human experts and semantic analysis of documents and published one paper in ACL 2020.
- Proposed a graph-based end-to-end learning framework to construct the taxonomy of missing domain.
- Knowledge Induction Team @ IBM Research AI
09/2015 - Present | Research Assistant | University of Connecticut
- Designed deep learning, machine learning methods to improve drug discovery & precision medicine.
- Constructed the graph convolutional networks on graphs for node embedding and graph embedding.
- Created various Generative Adversarial Networks (GANs) models on domain mappings, missing imputation, etc.
- Developed multi-view and multi-task algorithms that automatically detect disorder problems using daily living datasets.
- Explored contextual embedding of medical concepts from Electronic Health Records (EHRs) with Word2vec.
05/2018 - 09/2018 | Research Intern | JD AI Research, JD.COM Silicon Valley Research Center
- SAIL-JD Knowledge Graph Research Program
- Mentors: Dr. Jing Huang, Dr. Yun Tang, Dr. Xiaodong He.
- Proposed a novel end-to-end structure-aware convolutional network which incorporates graph connectivity structure seamlessly into a new convolutional translating embedding model for knowledge graph completion.
- Designed a new graph convolutional model utilizing knowledge graph structure, node attributes and relation types.
- Gained about 10% relative improvement over the state-of-the-art method, and published a KG completion framework.
05/2017 - 09/2017 | Research Assistant | Yale University
- Designed prominent machine learning methods, especially deep learning, for the early stage of drug design.
- Designed the molecular graph convolutional networks for learning molecular representations from undirected graphs.
- Extended Recurrent Neural Networks and Autoencoder models for SMILES strings, to learn sensible chemical rules and generate synthesizable molecules encoded as text sequences.
07/2014 - 11/2014 | Research Assistant | University of Southern California
- Data Science Laboratory
- Developed effective knowledge discovery and data mining techniques for emerging unstructured data.
- Implemented script codes to extract the patterns, relevant terms and its associated parameters.
03/2015 - 08/2015 | Research Intern | Institute of Automation, Chinese Academy of Sciences
- Built a high-performance computing platform on GPUs to accelerate deep learning research.
- Constructed deep learning models to extract image features.
09/2012 - 03/2015 | Research Assistant | Beijing University of Posts and Telecommunications
- Analyzed the limitations of Wireless Sensor Network, Information Centric Networking, etc.
- Design and simulate effective congestion control and scheduling algorithms.
Taxonomy Construction of Unseen Domains via Graph-based Cross-Domain Knowledge Transfer
Chao Shang, Sarthak Dash, Md Faisal Mahbub Chowdhury, Nandana Mihindukulasooriya, and Alfio Gliozzo. The 58th Annual Meeting of the Association for Computational Linguistics (ACL), 2020.
Consistent Edge-Aware Multi-View Spectral Graph Convolutions for Molecular Modeling
Chao Shang, Qinqing Liu, Qianqian Tong, Jiangwen Sun, Minghu Song, and Jinbo Bi. Under Review, 2020.
Predicting Outcomes of Chemical Reactions: A Seq2Seq Approach with Multi-view Attention and Edge Embedding
Xia Xiao, Chao Shang, Jinbo Bi and Sanguthevar Rajasekaran. International Joint Conference on Neural Networks (IJCNN), 2020.
End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
Chao Shang, Yun Tang, Jing Huang, Jinbo Bi, Xiaodong He, and Bowen Zhou. The AAAI Conference on Artificial Intelligence (AAAI), 2019. (acceptance rate of 16.2%) Code
Large-scale Automatic Depression Screening Using Meta-data from WiFi Infrastructure
Shweta Ware, Chaoqun Yue, Reynaldo Morillo, Jin Lu, Chao Shang, Jinbo Bi, Jayesh Kamath, Alexander Russell, Athanasios Bamis and Bing Wang. ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), 2019 (ACM Journal of IMWUT)
Predicting Depressive Symptoms Using Smartphone Data
Shweta Ware, Chaoqun Yue, Reynaldo Morillo, Jin Lu, Chao Shang, Jayesh Kamath, Athanasios Bamis, Jinbo Bi, Alexander Russell and Bing Wang. IEEE/ACM CHASE, 2019
Edge Attention-based Multi-Relational Graph Convolutional Networks
Chao Shang, Qinqing Liu, Ko-Shin Chen, Jiangwen Sun, Jin Lu, Jinfeng Yi, and Jinbo Bi. arXiv preprint arXiv:1802.04944, 2018. Code
Joint Modeling of Heterogeneous Sensing Data for Depression Assessment via Multi-task Learning
Jin Lu, Chao Shang, Chaoqun Yue, Reynaldo Morillo, and Shweta Ware, Jayesh Kamath, Athansios Bamis, Alexander Russell, Bing Wang, and Jinbo Bi. ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), 2018 (ACM Journal of IMWUT)
Fusing Location Data for Depression Prediction
Chaoqun Yue, Shweta Ware, Reynaldo Morillo, Jin Lu, Chao Shang, Jinbo Bi, Jayesh Kamath, Alexander Russell, Athanasios Bamis and Bing Wang. IEEE Transactions on Big Data (IEEE TBDATA), 2018.
VIGAN: Missing View Imputation with Generative Adversarial Networks
Chao Shang, Aaron Palmer, Jiangwen Sun, Ko-Shin Chen, Jin Lu, Jinbo Bi.
IEEE International Conference on Big Data (IEEE BigData), 2017 (acceptance rate of 18%) Code
Fusing Location Data for Depression Prediction
Chaoqun Yue, Shweta Ware, Reynaldo Morillo, Jin Lu, Chao Shang, Jinbo Bi, Jayesh Kamath, Alexander Russell, Athanasios Bamis and Bing Wang. IEEE Ubiquitous Intelligence & Computing (UIC), 2017
Event Extraction from Unstructured Text Data
Chao Shang, Anand Panangadan, and Victor K. Prasanna.
International Conference on Database and Expert Systems Applications (DEXA), 2015
A carrier class IoT service architecture integrating IMS with SWE
Dongliang Xie, Chao Shang, Jinchao Chen, Yongfang Lai, and Chuanxiao Pang.
International Journal of Distributed Sensor Networks (IJDSN), 2014
- SR1: Graph Neural Networks, CIKM 2019.
Program Committee / Reviewer
- Program Committee Member of EMNLP 2020.
- Program Committee Member of ACL 2020.
- Program Committee Member of IJCAI 2020.
- Program Committee Member of CIKM 2020.
- Program Committee Member of CIKM 2019.
- Program Committee Member of ECML-PKDD 2019.
- Program Committee Member of IJCAI 2019.
- Reviewer of IEEE Transactions on Neural Networks and Learning Systems (TNNLS).
- Reviewer of Journal of Artificial Intelligence Research (JAIR).
- Reviewer of IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB).
- Reviewer of American Medical Informatics Association (AMIA) Clinical Informatics Conference.
- Reviewer of PLOS ONE journal.
- External Reviewer: KDD’19; KDD’18; AAAI’18 and so on.
- 2020 Departmental Research Excellence Award
- 2019 Predoctoral Prize for Research Excellence
- 2019 AAAI Student Scholarship.
- 2018 Predoctoral Honorable Mention Award.
- 2018 the 4th Annual Graduate Poster Competition, Computer Science & Engineering First Place Award.
- 2017 IEEE International Conference on Big Data, Student Travel Award.
- 2014 National Scholarship for Graduate Students.
- CSE-1010 Introduction to Computing for Engineers (09/2016-05/2017)
- CSE-5820 Machine Learning (01/2017-05/2017)
X Machine Learning(XML) Group
The X Machine Learning (XML) group focuses on machine learning and deep learning algorithms for solving problems involving data with special structure, with an emphasis on healthcare informatics and bioinformatics.
Email: chao.shang AT uconn.edu
Address: 371 Fairfield Way, Unit 4155, Storrs, Conntecticut 06269