Tong Zhao

Understanding Generative Recommendation with Semantic IDs from a Model-scaling View

A Pre-training Framework for Relational Data with Information-theoretic Principles

Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning

One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs

Multimodal Attributed Graphs: Benchmarking and Rethinking

Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks

STRUCTDROP: A STRUCTURED RANDOM ALGORITHM TOWARDS EFFICIENT LARGE-SCALE GRAPH TRAINING

Node Duplication Improves Cold-start Link Prediction