I'm an assistant professor in the Department of Computer Science and Engineering at the University of Notre Dame. My research focuses on Computational Behavior Modeling for applications such as recommendation, fraud detection, question answering, and decision making. It is at the intersection of data mining, machine learning, natural language processing, and artificial intelligence. [C.V.]

Call for Journal Articles: I am a co-Topic Editor for the Research Topic "Computational Behavioral Modeling for Big User Data" in Big Data Networks, Frontiers in Big Data. Keywords: Recommender Systems, Misbehavior Detection, Social Network Analysis, Graph Learning. Deadline: June 15, 2021.

Our survey on Knowledge-Enhanced Text Generation is released on arXiv. Here is the long reading list! (This GitHub page has over 250+ stars.)

Our KDD 2020 Tutorial on Scientific Text Mining and Knowledge Graphs is released. Click and find slides and videos!

I am directing the Data Mining towards Decision Making (DM2) Laboratory. My research has been supported by National Science Foundation, Condé Nast Inc., Snap Inc. Research, and Notre Dame Global Gateway.

• NSF CRII: III: Complementarity Learning for Contextual Behavior Modeling. (10/01/2019 - 09/30/2021)
• NSF SHF: Medium: Collaborative Research: Semantically-Enhanced Software Traceability for Supporting Human-Centric Tasks. (08/15/2019 - 08/14/2023)

I am recruiting PhD students and visiting researchers. Drop me an e-mail (mjiang2 [at] nd.edu) if you are interested! Stay healthy, safe, and happy!

What's New

• Check our Github repositories: DM2 @ Github --
• March 2021: One paper was accepted to ACM TIST on learning complementarity.
• March 2021: Two papers were accepted to NAACL-HTL 2021 on abstractive summarization and technical question answering.
• February 2021: One paper was accepted to ACM TOIS on graph representation learning.
• January 2021: Two papers were accepted to TheWebConf 2021.
• December 2020: Congratulations to Tong Zhao for receiving 2020 Snap Research Fellowship.
• December 2020: Congratulations to Bo Ni for receiving honorable mention, Computing Research Association's (CRA) Outstanding Undergraduate Researcher Award!
• December 2020: One paper was accepted to ICSE 2021 on Transformer models for software traceability.
• December 2020: One paper was accepted to AAAI 2021 on Data Augmentation for Graph Neural Networks.
• November 2020: One paper was accepted to IEEE TKDE on representation learning.
• November 2020: One paper was accepted to Science Advances (impact factor 2020: 12.530) on transfer learning.
• September 2020: Three papers were accepted to EMNLP 2020 on information extraction, relation reasoning, and text generation, including a TechQA demo system: [github] [video]
• August 2020: Congratulations to Daheng Wang and co-authors for winning the Best Paper Award in the International Workshop on Deep Learning on Graphs: Methods and Applications (KDD-DLG'20), entitled Learning Attribute-Structure Co-Evolutions in Dynamic Graphs.

Latest Publications

• Modeling Complementarity in Behavior Data with Multi-Type Itemset Embedding, ACM Transactions on Intelligent Systems and Technology, 2021.
• Inductive Contextual Relation Learning for Personalization, ACM Transactions on Information Systems, 2021.
• Technical Question Answering across Tasks and Domains, NAACL-HLT, 2021.
• Enhancing Factual Consistency of Abstractive Summarization, NAACL-HLT, 2021.
• TCN: Table Convolutional Network for Web Table Interpretation, TheWebConf, 2021.
• Few-Shot Graph Learning for Molecular Property Prediction, TheWebConf, 2021.
• Traceability Transformed: Generating More Accurate Links with Pre-Trained BERT Models, ICSE, 2021.
• Data Augmentation for Graph Neural Networks, AAAI, 2021.
• A Survey of Knowledge-Enhanced Text Generation, Preprint: arXiv: 2010.04389, 2020. (Long reading list) Led by Wenhao Yu and collaborated with Dr. Chenguang Zhu (Microsoft Research), Dr. Zhiting Hu (UCSD), and Dr. Heng Ji (UIUC).
• Structural and Textual Information Fusion for Symptom and Disease Representation Learning, IEEE Transactions on Knowledge and Data Engineering, 2020. (In press, IF=4.935)
• Leverage Electron Properties to Predict Phonon Properties via Transfer Learning for Semiconductors, Science Advances, 2020. (IF=12.530)
• Biomedical Knowledge Graphs Construction from Conditional Statements, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020.
• Precise Temporal Slot Filling via Truth Finding with Data-Driven Commonsense, Knowledge and Information Systems, 2020.
• Phrase-level Pairwise Topic Modeling to Uncover Helpful Peer Responses to Online Suicidal Crises, Nature Humanities and Social Sciences Communications, 2020.
• A Technical Question Answering System with Transfer Learning, EMNLP, 2020. (demo) [github] [video]
• Tri-Train: Automatic Pre-fine Tuning between Pre-training and Fine-tune Training for SciNER, EMNLP-Findings, 2020.
• Error-bounded Graph Anomaly Loss for GNNs, CIKM, 2020.
• GraSeq: Graph and Sequence Fusion Learning for Molecular Property Prediction, CIKM, 2020.
• Learning Attribute-Structure Co-Evolutions in Dynamic Graphs, KDD-DLG, 2020. (best paper award)
• Early Fraud Detection with Augmented Graph Learning, KDD-DLG, 2020.
• GNN-based Graph Anomaly Detection with Graph Anomaly Loss, KDD-DLG, 2020.
• Scientific Text Mining and Knowledge Graphs, KDD, 2020. (tutorial)
• Multi-modal Network Representation Learning: Methods and Applications, KDD, 2020. (tutorial)
• Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors, KDD, 2020.
• Crossing Variational Autoencoders for Answer Retrieval, ACL, 2020.
• Identifying Referential Intention with Heterogeneous Contexts, TheWebConf, 2020.
• Experimental Evidence Extraction in Data Science with Hybrid Table Features and Ensemble Learning, TheWebConf, 2020.
• Few-Shot Knowledge Base Completion, AAAI, 2020.
• Graph Few-shot Learning via Knowledge Transfer, AAAI, 2020.

Completed Projects

• Global Gateway: Digital Empires: Structured Biographical and Social Network Analysis of Early Chinese Empires. (05/01/2019 - 08/31/2020)
• Condé Nast: Representation Learning for Modeling and Predicting User Engagement and Propensity for Conversion Through the Engagement Funnel. (01/21/2019 - 05/20/2020)

Last updated on March 24, 2021.