60 citations · 88 across the 15 of their papers we have counts for
7 papers · 1 filter
Distances for Markov Chains, and Their Differentiation
Tristan Brugère, Zhengchao Wan, Yusu Wang
(Directed) graphs with node attributes are a common type of data in various applications and there is a vast literature on developing metrics and efficient algorithms for comparing…
Understanding Oversquashing in GNNs through the Lens of Effective Resistance
Mitchell Black, Zhengchao Wan, Amir Nayyeri +1
Message passing graph neural networks (GNNs) are a popular learning architectures for graph-structured data. However, one problem GNNs experience is oversquashing, where a GNN has…
The Weisfeiler-Lehman Distance: Reinterpretation and Connection with GNNs
Samantha Chen, Sunhyuk Lim, Facundo Mémoli +2
In this paper, we present a novel interpretation of the so-called Weisfeiler-Lehman (WL) distance, introduced by Chen et al. (2022), using concepts from stochastic processes. The W…
The Numerical Stability of Hyperbolic Representation Learning
Gal Mishne, Zhengchao Wan, Yusu Wang +1
Given the exponential growth of the volume of the ball w.r.t. its radius, the hyperbolic space is capable of embedding trees with arbitrarily small distortion and hence has receive…
Weisfeiler-Lehman meets Gromov-Wasserstein
Samantha Chen, Sunhyuk Lim, Facundo Mémoli +2
The Weisfeiler-Lehman (WL) test is a classical procedure for graph isomorphism testing. The WL test has also been widely used both for designing graph kernels and for analyzing gra…
The Gaussian Transform
Kun Jin, Facundo Mémoli, Zhengchao Wan
We introduce the Gaussian transform (GT), an optimal transport inspired iterative method for denoising and enhancing latent structures in datasets. Under the hood, GT generates a n…
The Wasserstein transform
Kun Jin, Facundo Mémoli, Zane Smith +1
We introduce the Wasserstein Transform (WT), a general unsupervised framework for updating distance structures on given data sets with the purpose of enhancing features and denoisi…