Chuxu Zhang / 张初旭
Associate Professor of Computer Science and Engineering
Director, MINDS Lab
School of Computing, College of Engineering
University of Connecticut (UConn)
352 Mansfield Rd, Storrs, CT 06269, USA
chuxu.zhang@uconn.edu
News
About
I am an Associate Professor of Computer Science and Engineering at University of Connecticut. My research interests center around machine learning and data science. Recently, I have focused on developing foundational, resource-efficient, and safe machine learning algorithms and models, particularly on graph and language data. Besides, I apply them to applications in various domains including public health, healthcare, social media, and others. My works are majorly published in top conferences of machine learning and data science (e.g., ICML, NeurIPS, ICLR, and KDD). I direct the Machine Intelligence and Data Science (MINDS) Lab.
I have received some awards and honors such as the NSF CAREER Award (2024), the Frontiers of Science Award (2024), and the AAAI New Faculty Highlight (2023). Besides, my work won several Best Paper Awards or nominations in major conferences.
Before joining UConn, I was an Assistant Professor of Computer Science at Brandeis University (2020-2024). I completed my PhD in Computer Science and Engineering at the University of Notre Dame (2017-2020), advised by Professor Nitesh Chawla.
My family lives in the Greater New York area.
Recent Publications
Here are a few of my recent publications. Please see my Google Scholar page for a complete list. ICML'25:
MASS: MAthematical Data Selection via Skill Graphs for Pretraining Large Language Models
ICML'25:
Beyond Message Passing: Neural Graph Pattern Machine
ICML'25:
Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
ACL'25:
NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning
NAACL'25:
Can LLMs Convert Graphs to Text-Attributed Graphs?
KDD'25:
A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation
NeurIPS'24:
GFT: Graph Foundation Model with Transferable Tree Vocabulary
ICML'24:
From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble
ICLR'24:
Mitigating Emergent Robustness Degradation While Scaling Graph Learning
KDD'24:
Diet-ODIN: A Novel Framework for Opioid Misuse Detection with LLM-based Interpretable Dietary Patterns
KDD'24:
Graph Cross Supervised Learning via Generalized Knowledge
ICML'23:
When Sparsity Meets Contrastive Models: Less Graph Data Can Bring Better Class-Balanced Representations
ICLR'23:
Chasing All-Round Graph Representation Robustness: Model, Training, and Optimization
ICLR'23:
Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
ICLR'23:
Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency