Shuiwang Ji

About

Shuiwang Ji is a Professor in the Department of Computer Science & Engineering at Texas A&M University. He holds the Truchard Family Endowed Chair, is a Presidential Impact Fellow, and an EDGES Fellow. His educational background includes a Ph.D. in Computer Science from Arizona State University, obtained in 2010. His research interests focus on machine learning and artificial intelligence (AI) for science and engineering, with particular emphasis on language models and agents. He is a Fellow of the Institute of Electrical and Electronics Engineers (IEEE) since 2023 and a Fellow of the American Institute for Medical and Biological Engineering (AIMBE) since 2022. His contributions to the field have been recognized through numerous awards, including the Distinguished Achievement Award from Texas A&M University and The Association of Former Students in 2026, the Dean of Engineering Excellence Award in 2024, and the NSF CAREER Award in 2014. His work involves advancing AI methodologies for scientific applications, contributing to the development of tensor decomposition networks, geometry-informed tokenization of molecules, and invariant tokenization of crystalline materials, among other areas.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Theoretical computer science

Selected publications

• Explainability in Graph Neural Networks: A Taxonomic Survey

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2022 · 493 citations

  Senior authorCorresponding

  Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumvented by developing post hoc techniques to explain predictions, giving rise to the area of explainability. Recently, explainability of deep models on images and texts has achieved significant progress. In the area of graph data, graph neural networks (GNNs) and their explainability…

  DOI

• Self-Supervised Learning of Graph Neural Networks: A Unified Review

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2022 · 358 citations

  Senior authorCorresponding

  Deep models trained in supervised mode have achieved remarkable success on a variety of tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a new paradigm for making use of large amounts of unlabeled samples. SSL has achieved promising performance on natural language and image learning tasks. Recently, there is a trend to extend such success to graph data using graph neural networks (GNNs). In this survey, we provide a unified review of different ways of traini…

  DOI

• Line Graph Neural Networks for Link Prediction

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2021 · 235 citations

  Senior authorCorresponding

  We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. With the advances of deep learning, current link prediction methods commonly compute features from subgraphs centered at two neighboring nodes and use the features to predict the label of the link between these two nodes. In this formalism, a link prediction problem is converted to a graph classification task. In order to extract fixed-size features for classification, graph…

  DOI

• Artificial intelligence for science in quantum, atomistic, and continuum systems

  Foundations and Trends® in Machine Learning · 2025-07-21 · 10 citations

  articleSenior author

  Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and tec…

  PublisherDOI

• Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation

  ArXiv.org · 2025-02-28 · 2 citations

  preprintOpen accessSenior author

  We consider the problem of crystal materials generation using language models (LMs). A key step is to convert 3D crystal structures into 1D sequences to be processed by LMs. Prior studies used the crystallographic information framework (CIF) file stream, which fails to ensure SE(3) and periodic invariance and may not lead to unique sequence representations for a given crystal structure. Here, we propose a novel method, known as Mat2Seq, to tackle this challenge. Mat2Seq converts 3D crystal struc…

  PublisherOA PDFDOI

Recent grants

• III: Medium: Collaborative Research: Towards Scalable and Interpretable Graph Neural Networks

  NSF · $100k · 2020–2022

• Collaborative Research: ABI Innovation: Towards Computational Exploration of Large-Scale Neuro-Morphological Datasets

  NSF · $296k · 2017–2020

• III: Small: Collaborative Research: Demystifying Deep Learning on Graphs: From Basic Operations to Applications

  NSF · $263k · 2020–2024

Frequent coauthors

• Jieping Ye

  66 shared

• Zhengyang Wang

  42 shared

• Sudhir Kumar

  Malaviya National Institute of Technology Jaipur

  40 shared

• Hongyang Gao

  31 shared

• Yaochen Xie

  Texas A&M University

  28 shared

• Stuart J. Newfeld

  Arizona State University

  27 shared

• Youzhi Luo

  Texas A&M University

  25 shared

• Michael McCutchan

  Arizona State University

  25 shared

Education

• PhD, Computer Science and Engineering

  Arizona State University

Awards & honors

• Distinguished Achievement Award for research, Texas A&M Univ…
• Dean of Engineering Excellence Award, Texas A&M University (…
• Computer Science & Engineering Graduate Faculty Teaching Exc…
• IEEE Transactions on Pattern Analysis and Machine Intelligen…
• Faculty Early Career Development (CAREER) Award, National Sc…

Similar researchers at Texas A&M University

• Thomas R. Ioergerh-60
• Jianer Chenh-49
• Guofei Guh-47