Tengfei Ma (马腾飞)

Research Staff Member

IBM T. J. Watson Research Center

Email: tengfei.ma1 (at) ibm (dot) com




About Me

I am a research staff member in IBM T. J. Watson Research Center, New York, USA. I joined IBM Research-Tokyo in 2015 and then moved to the US in 2016. Prior to that, I obtained my PhD degree from the Graduate School of Information Science and Technology, the University of Tokyo, Japan, under the supervision of Prof. Hiroshi Nakagawa. I received my M.S. from Peking University (where I was supervised by Prof. Xiaojun Wan) and my B.E. from Tsinghua University, China.

My research interests include machine learning, natural language processing (NLP) and bioinformatics. In particular, I have been working on document summarization, Bayesian nonparametrics, deep learning. Currently my research is mainly focused on graph neural networks, and I am also interested in other deep learning techniques in healthcare and NLP areas.

Recent News:

  • 12/2022: Our paper "An Analysis of Virtual Nodes in Graph Neural Networks for Link Prediction (Extended Abstract)" has been accepted by The First Learning on Graphs Conference (Log2022) for a spotlight presentation.

  • 11/2022: I am invited to give a talk on "Machine Learning Techniques to Follow DFU Progress" in the Diabetic Lower Extremity Symposium. In this talk I will introduce our effort using machine learning to accelerate wound healing, e.g. how neural symbolic models help with interpretable time series classification and factor selection.

  • 9/2022: Our paper "Neural Approximation of Extended Persistent Homology on Graphs" is accepted by NeurIPS 2022.

  • 9/2022: One paper about neural logic models for time series classification is accepted by ICDM2o22.

  • 8/2022: I am invited to give a talk on "Graph learning with geometric and topological structures" at the AI Seminar of USC.

  • 5/2022: One paper about knowledge graph rule learning (using cycles) is accepted by ICML2022!

  • 4/2022: One paper is accepted by NAACL2022 main conference.

  • 1/2022: Our paper "GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks" is accepted by TVCG. It is the first tool to visualize the GNN results and it can help people identify possible data and model error patterns. This tool has been integrated into DGL https://github.com/dmlc/GNNLens2

  • 11/2021: One paper titled "MalGraph: Hierarchical Graph Neural Networks for Robust Windows Malware Detection" has been accepted by IEEE INFOCOM'22!

  • 10/2021: Our paper "Improving Inductive Link Prediction Using Hyper-relational Facts" won the best paper award in ISWC2021!