Generative Graph Pattern Machine
Published in neural information processing systems • Jan 1, 2025
Authors:,,
Zehong Wang
Zheyuan Zhang
Tianyi Ma
Abstract
Graph neural networks (GNNs) have been predominantly driven by message-passing, where node representations are iteratively updated via local neighborhood aggregation. Despite their success, message-passing suffers from fundamental limitations -- including constrained expressiveness, over-smoothing, ...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!