About Me

Welcome! I am now a Data Scientist working at the Home Depot. I received my Ph.D. degree in Computer Science at Emory University. My Ph.D. advisor is Dr. Liang Zhao. I earned my B.S. degree in Computer Science from Shandong University, China in 2014, and M.S. in Computer Science from George Mason University in 2018 with the Distinguished Academic Achievement. My research focuses on data mining and machine learning techniques that can handle complex structured data, such as spatiotemporal and graph-structured data. In addition, I am also interested in opening the ‘black-box’ of the deep learning models via designing the bio-inspired model architectures as well as via enhancing their interpretability and explainability through new technique called Explanation-Guided Learning (EGL). Check out our latest survey on GEL here!

I have published many peer-reviewed full research papers in top-tier conferences and journals such as KDD, AAAI, ICDM, TKDD, TKDE, and Neural Networks. I have also served as the Independent Reviewer and PC member for many top-tier conferences and journals such as KDD, AAAI, CSCW, TKDD, JMLR, TNNLS, and TOIS. You can find more about my works in my Publication, and more about me in my CV.

News

• 12/2022: Our systematic survey paper on explanation-guided learning (EGL) is available online at Arxiv here!
• 08/2022: One paper about explanation supervsion has been accepted by CSCW 2022! Paper, code, as well as our human-labeled explanation data are now available at Github here!
• 06/2022: Serve as the Independent Reviewer for journals TNNLS and TKDD.
• 05/2022: Our new work on robust visual explanation supervision has been accepted by KDD 2022! Paper, code, as well as our human-labeled explanation data are now available at Github here!
• 03/2022: Serve as the PC member for KDD 2022.
• 03/2022: Serve as the Independent Reviewer for journals TOIS, TKDD, JMLR.
• 02/2022: Serve as the PC member for CSCW 2022.
• 09/2021: Serve as the PC member for AAAI 2022.
• 08/2021: Our paper on learning to explain GNNs has been accepted by ICDM 2021! Paper, code, as well as our human-labeled explanation data are now available at Github here!