Google Scholar
Education
PhD, Computer Science, Michigan State University
MS, Computer Science, Pennsylvania State University
BS, Computer Science, Pennsylvania State University
BS, Mathematical Sciences, Pennsylvania State University
About
Dr. Tyler Derr is an Assistant Professor of Computer Science in the College of Connected Computing at Vanderbilt University, where he directs the Network and Data Science (NDS) Lab. His research focuses on graph machine learning, large language models and AI agents, data-centric AI, and trustworthy and responsible AI, with applications to social networks, recommender systems, and computational drug discovery. His work has appeared in leading venues in data mining, machine learning, and artificial intelligence, with 75+ publications and more than 5,000 citations.
Dr. Derr’s research has been recognized with an NSF CAREER Award, International Neural Network Society’s Aharon Katzir Young Investigator Award, NVIDIA Academic Grant Program Award, IJCAI-ECAI Early Career Spotlight, and several best paper and influential paper distinctions. He serves as an Associate Editor for ACM TKDD, IEEE Transactions on Big Data, and Tsinghua Science and Technology, and has held organizing roles for KDD, CIKM, SDM, DSAA, and WSDM. At Vanderbilt, he also serves as a Faculty Senator and Co-Chair of the Academic Policies and Services Committee. He has delivered 45+ invited talks at leading universities, major conferences, and research laboratories worldwide, and presented tutorials at AAAI, KDD, CIKM, and SDM. Under his mentorship, students have earned competitive university awards, federal fellowships, and ACM distinctions. His contributions to teaching and mentorship have been recognized with Vanderbilt’s 2020 School of Engineering Teaching Innovation Award and 2025 Career Catalyst Impact Award, for which he was the university’s sole faculty recipient.
Research Focus
Graph Machine Learning
Large Language Models and AI Agents
Trustworthy and Responsible AI
Publications
Knowledge Graph Prompting for Multi-Document Question Answering — AAAI 2024; Best Paper Award, New Frontiers in Graph Learning Workshop at NeurIPS 2023.
Collaboration-Aware Graph Convolutional Network for Recommender Systems — The Web Conference 2023; ranked #9 among Paper Digest’s Most Influential WWW’23 Papers.
Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage — KDD 2022.