Biography

I am a CS Ph.D. student at Purdue University advised by Professor Bruno Ribeiro in the PurdueMINDS Lab. Before joining Purdue, I was working with Professor Paul Rosenbloom and Dr. Volkan Ustun at the Sigma cognitive architecture lab in the USC Institute for Creative Technologies. I received the Computer Science Outstanding Student Award from USC Viterbi School of Engineering when graduating with a B.S. degree in CS.

I am currently interested in graph representation learning and its application to reasoning in knowledge graphs, causal inference and causal structural discovery, meta learning, and artificial general intelligence. My past research has also involved cognitive architectures, multi-agent reinforcement learning, and probabilistic graphical models & programming. I believe research breakthroughs in all these areas will be critical to the development of a next-generation integrated architecture of artificial general intelligence.

Download my Curriculum Vitae .

Contact me: zhou791 at purdue dot edu

Interests
  • Graph Representation Learning
  • Knowledge Graphs
  • Causal Inference & Causal Structural Discovery
  • Meta Learning
  • Cognitive Architectures
  • Artificial General Intelligence
Education
  • Ph.D. in Computer Science (in progress), 2027 (expected)

    Purdue University

  • MS in Computer Science, 2022

    University of Southern California

  • BS in Computer Science, 2021

    University of Southern California

  • BS in Mathematics, 2021

    University of Southern California

Publications

(2024). Zero-shot Logical Query Reasoning on any Knowledge Graph. Arxiv Preprint.

PDF Cite Code

(2024). Long-Range Synthetic Knowledge Graph Benchmarks for Double-Equivariant Models. ICLR 2024 BGPT.

PDF Cite

(2023). Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Types. NeurIPS 2023 New Frontiers in Graph Learning (GLFrontiers) (Oral).

PDF Cite Code Workshop Page Poster Slides

(2023). An OOD Multi-Task Perspective for Link Prediction with New Relation Types and Nodes. NeurIPS 2023 New Frontiers in Graph Learning (GLFrontiers).

PDF Cite Workshop Page Poster