Výsledky vyhledávání - "Li, Shouheng"

Report

Towards Bridging Generalization and Expressivity of Graph Neural Networks

Autor: Li, Shouheng, Geerts, Floris, Kim, Dongwoo, Wang, Qing

Expressivity and generalization are two critical aspects of graph neural networks (GNNs). While significant progress has been made in studying the expressivity of GNNs, much less is known about their generalization capabilities, particularly when dea

Externí odkaz: http://arxiv.org/abs/2410.10051

Zobrazit plný text záznamu

Report

Generalization of Graph Neural Networks through the Lens of Homomorphism

Autor: Li, Shouheng, Kim, Dongwoo, Wang, Qing

Despite the celebrated popularity of Graph Neural Networks (GNNs) across numerous applications, the ability of GNNs to generalize remains less explored. In this work, we propose to study the generalization of GNNs through a novel perspective - analyz

Externí odkaz: http://arxiv.org/abs/2403.06079

Zobrazit plný text záznamu

Report

Local Vertex Colouring Graph Neural Networks

Autor: Li, Shouheng, Kim, Dongwoo, Wang, Qing

Publikováno v: Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19616-19637, 2023

In recent years, there has been a significant amount of research focused on expanding the expressivity of Graph Neural Networks (GNNs) beyond the Weisfeiler-Lehman (1-WL) framework. While many of these studies have yielded advancements in expressivit

Externí odkaz: http://arxiv.org/abs/2403.06080

Zobrazit plný text záznamu

Report

Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering

Autor: Li, Shouheng, Kim, Dongwoo, Wang, Qing

While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little has been done on adapting classical GNNs to less-homophilic graphs. Although the ability to handle less

Externí odkaz: http://arxiv.org/abs/2206.02386

Zobrazit plný text záznamu