paper-with-me

홈 › Papers

Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling

2022-07-07 · Hongkang Li, Meng Wang, Sijia Liu, Pin-Yu Chen, JinJun Xiong

Graph convolutional networks (GCNs) have recently achieved great empirical success in learning graph-structured data. To address its scalability issue due to the recursive embedding of neighboring features, graph topology sampling has been proposed to reduce the memory and computational cost of training GCNs, and it has achieved comparable test performance to those without topology sampling in many empirical studies. To the best of our knowledge, this paper provides the first theoretical justification of graph topology sampling in training (up to) three-layer GCNs for semi-supervised node classification. We formally characterize some sufficient conditions on graph topology sampling such that GCN training leads to a diminishing generalization error. Moreover, our method tackles the nonconvex interaction of weights across layers, which is under-explored in the existing theoretical analyses of GCNs. This paper characterizes the impact of graph structures and topology sampling on the generalization performance and sample complexity explicitly, and the theoretical findings are also justified through numerical experiments.

📄 PDF Abstract BibTeX arXiv:2207.03584

Code (0)

등록된 구현이 없습니다.

Tasks

Node Classification

Methods 이 논문이 사용한 방법론

Test 설명 없음
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Stability and Generalization of Graph Convolutional Neural Networks

2019-05-03 · Saurabh Verma, Zhi-Li Zhang

Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world dat…

Generalization BoundsGraph Learning

Graph Convolutional Kernel Machine versus Graph Convolutional Networks

2023-09-21 · NeurIPS 2023 11

Graph convolutional networks (GCN) with one or two hidden layers have been widely used in handling graph data that are prevalent in various disciplines. Many studies showed that the gain of making GCNs deeper is tiny or …

PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification

2025-09-08 · Huayi Tang, Yong Liu arxiv

Graph neural networks (GNNs) have achieved remarkable success in processing graph-structured data across various applications. A critical aspect of real-world graphs is their dynamic nature, where new nodes are continual…

Node Classification

LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL

2021-09-29 · ICLR 2022 4 · Wei Lu

An abundance of neural network models and algorithms for diverse tasks on graphs have been developed in the past five years. However, very few provable guarantees have been available for the performance of graph neural n…

Community DetectionGraph Neural NetworkStochastic Block Model

A Manifold Perspective on the Statistical Generalization of Graph Neural Networks

2024-06-07 · Zhiyang Wang, Juan Cervino, Alejandro Ribeiro

Graph Neural Networks (GNNs) extend convolutional neural networks to operate on graphs. Despite their impressive performances in various graph learning tasks, the theoretical understanding of their generalization capabil…

Generalization BoundsGraph Learning