111 citations · 294 across the 18 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2023
A Graph Dynamics Prior for Relational Inference
Liming Pan, Cheng Shi, Ivan Dokmanić
Relational inference aims to identify interactions between parts of a dynamical system from the observed dynamics. Current state-of-the-art methods fit the dynamics with a graph ne…
cs.LG2022★ 1 cited
Homophily modulates double descent generalization in graph convolution networks
Cheng Shi, Liming Pan, Hong Hu +1
Graph neural networks (GNNs) excel in modeling relational data such as biological, social, and transportation networks, but the underpinnings of their success are not well understo…
cs.LG2021★ 12 cited
Neural Link Prediction with Walk Pooling
Liming Pan, Cheng Shi, Ivan Dokmanić
Graph neural networks achieve high accuracy in link prediction by jointly leveraging graph topology and node attributes. Topology, however, is represented indirectly; state-of-the-…