paper-with-me

홈 › Papers

A Local Graph Limits Perspective on Sampling-Based GNNs

2023-10-17 · Yeganeh Alimohammadi, Luana Ruiz, Amin Saberi

We propose a theoretical framework for training Graph Neural Networks (GNNs) on large input graphs via training on small, fixed-size sampled subgraphs. This framework is applicable to a wide range of models, including popular sampling-based GNNs, such as GraphSAGE and FastGCN. Leveraging the theory of graph local limits, we prove that, under mild assumptions, parameters learned from training sampling-based GNNs on small samples of a large input graph are within an $\epsilon$-neighborhood of the outcome of training the same architecture on the whole graph. We derive bounds on the number of samples, the size of the graph, and the training steps required as a function of $\epsilon$. Our results give a novel theoretical understanding for using sampling in training GNNs. They also suggest that by training GNNs on small samples of the input graph, practitioners can identify and select the best models, hyperparameters, and sampling algorithms more efficiently. We empirically illustrate our results on a node classification task on large citation graphs, observing that sampling-based GNNs trained on local subgraphs 12$\times$ smaller than the original graph achieve comparable performance to those trained on the input graph.

📄 PDF Abstract BibTeX arXiv:2310.10953

Code (0)

등록된 구현이 없습니다.

Tasks

Node Classification

Methods 이 논문이 사용한 방법론

FastGCN 설명 없음
GraphSAGE GraphSAGE is a general inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen…

Similar Papers 제목 키워드 기반

Limits, approximation and size transferability for GNNs on sparse graphs via graphops

2023-06-07 · NeurIPS 2023 11

Can graph neural networks generalize to graphs that are different from the graphs they were trained on, e.g., in size? In this work, we study this question from a theoretical perspective. While recent work established su…

Rethinking Graph Neural Networks for the Graph Coloring Problem

2022-08-15 · Wei Li, Ruxuan Li, Yuzhe ma, Siu On Chan 외

Graph coloring, a classical and critical NP-hard problem, is the problem of assigning connected nodes as different colors as possible. However, we observe that state-of-the-art GNNs are less successful in the graph color…

LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence

2023-02-02 · Zhihao Shi, Xize Liang, Jie Wang

The message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. However, training GNNs on large-scale graphs suffers from the well-known neighbor explosion problem, i.e…

Generalization and Representational Limits of Graph Neural Networks

2020-02-14 · ICML 2020 1 · Vikas K. Garg, Stefanie Jegelka, Tommi Jaakkola

We address two fundamental questions about graph neural networks (GNNs). First, we prove that several important graph properties cannot be computed by GNNs that rely entirely on local information. Such GNNs include the s…

Generalization Bounds

Bayesian Graph Neural Networks with Adaptive Connection Sampling

2020-06-07 · ICML 2020 1 · Arman Hasanzadeh, Ehsan Hajiramezanali, Shahin Boluki, Mingyuan Zhou 외

We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs. The proposed framework not only alleviates ov…

Node Classification