← Search

Wengang Guo

2 accepted papers

2026

Fast Mixture of Curvature-Aware Experts for Diverse and Dynamic Graph Topologies

ICML 2026poster

Dynamic graph learning, which focuses on modeling the merging, vanishing, and reconnection of nodes and edges, is crucial for real-world applications. In dynamic graphs, node neighborhoods often exhibit diverse and time-evolving topologies, including hierarchical, grid-like, and cyclic patterns. Exi…

Cited by 0SourceScholar
2024

PICNN: A Pathway towards Interpretable Convolutional Neural Networks

AAAI 2024technical

Convolutional Neural Networks (CNNs) have exhibited great performance in discriminative feature learning for complex visual tasks. Besides discrimination power, interpretability is another important yet under-explored property for CNNs. One difficulty in the CNN interpretability is that filters and…