Jundong Li

About

Jundong Li is an Associate Professor at the University of Virginia, with primary appointments in the Department of Electrical and Computer Engineering and secondary appointments in the Department of Computer Science. Since summer 2022, he has also served as a part-time Research Scholar at LinkedIn. He earned his Ph.D. in Computer Science from Arizona State University in 2019 under the supervision of Dr. Huan Liu, after completing his M.Sc. in Computer Science at the University of Alberta in 2014 and his B.Eng. in Software Engineering at Zhejiang University in 2012. His research interests encompass data mining, machine learning, and artificial intelligence, with particular emphasis on graph machine learning, trustworthy and safe machine learning, and large language models. He has published over 200 papers in high-impact venues, receiving more than 20,000 citations, and has been recognized with several early career awards, including the NSF CAREER Award in 2022, the SIGKDD Rising Star Award in 2024, and the ICDM Tao Li Award in 2025. His research is supported by various industry and government agencies, including UVA, NSF, DOE, ONR, and others.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Theoretical computer science
• Information Retrieval
• Data Mining
• Natural Language Processing
• Computer network
• World Wide Web

Selected publications

• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation

  2021 · 480 citations

  Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences. However, real-life interactions among users are very complex and user relations can be high-order. Hypergraph provides a natural way to model high-order relations, while its potentials for improving social recommendation are under-explored. In this paper, we fil…

  DOI

• Line Graph Neural Networks for Link Prediction

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

  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

• Be More with Less: Hypergraph Attention Networks for Inductive Text Classification

  2020 · 210 citations

  Text classification is a critical research topic with broad applications in natural language processing. Recently, graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on this canonical task. Despite the success, their performance could be largely jeopardized in practice since they are: (1) unable to capture high-order interaction between words; (2) inefficient to handle large datasets and new documents. To address tho…

  DOI

• MI4Rec: Pretrained Language Model based Cold-Start Recommendation with Meta-Item Embeddings

  2025-11-08 · 2 citations

  articleOpen accessSenior author

  Recently, pretrained large language models (LLMs) have been widely adopted in recommendation systems to leverage their textual understanding and reasoning abilities to model user behaviors and suggest future items. A key challenge in this setting is that items on most platforms are not included in the LLM's training data. Therefore, existing methods often fine-tune LLMs by introducing auxiliary item tokens to capture item semantics. However, in real-world applications such as e-commerce and shor…

  PublisherDOI

• Graph Foundation Models: Challenges, Methods, and Open Questions

  2025-08-03 · 2 citations

  articleOpen access

  Foundation models have revolutionized machine learning by enabling general-purpose reasoning across diverse tasks and domains. These models, pretrained on large-scale data, demonstrate strong adaptability with minimal task-specific supervision, leading to breakthroughs in natural language processing and computer vision. Inspired by this paradigm, Graph Foundation Models (GFMs) have emerged to extend the benefits of foundation models to graph-structured data, which is pretrained on massive graphs…

  PublisherOA PDFDOI

Recent grants

• CAREER: Toward A Knowledge-Guided Framework for Personalized Decision Making

  NSF · $616k · 2022–2027

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

  NSF · $269k · 2020–2025

Frequent coauthors

• Huan Liu

  82 shared

• Wei Wei

  Sun Yat-sen University Cancer Center

  64 shared

• Yushun Dong

  48 shared

• Kaize Ding

  Northwestern University

  47 shared

• Jilei Zhang

  Jinan University

  39 shared

• Jihong Liu

  Sun Yat-sen University

  36 shared

• Jing Chen

  Anhui Agricultural University

  35 shared

• Minnan Luo

  35 shared

Labs

• Jundong Li's LabPI

  Not provided

Awards & honors

• ICDM Tao Li Award (2025)
• SIGKDD Rising Star Award (2024)
• PAKDD Early Career Research Award (2023)
• NSF CAREER Award (2022)
• PAKDD Best Paper Award (2024)

Similar researchers at University of Virginia

• Kevin Skadronh-63
• David Evansh-61
• Qizhe Caih-57