Generalization bounds for graph convolutional neural networks via Rademacher complexity
This paper aims at studying the sample complexity of graph convolutional networks (GCNs), by providing tight upper bounds of Rademacher complexity for GCN models with a single hidden layer. Under regularity conditions, theses derived complexity bounds explicitly depend on the largest eigenvalue of graph convolution filter and the degree distribution of the graph. Again, we provide a lower bound of Rademacher complexity for GCNs to show optimality of our derived upper bounds. Taking two commonly used examples as representatives, we discuss the implications of our results in designing graph convolution filters an graph distribution.
Code (1)
Tasks
Generalization BoundsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Rademacher Complexity-based Generalization Bounds for Deep Learning
We show that the Rademacher complexity-based approach can generate non-vacuous generalisation bounds on Convolutional Neural Networks (CNNs) for classifying a small number of classes of images. The development of new Tal…
Deep LearningGeneralization BoundsRademacher Complexity Bounds for Non-I.I.D. Processes
This paper presents the first data-dependent generalization bounds for non-i.i.d. settings based on the notion of Rademacher complexity. Our bounds extend to the non-i.i.d. case existing Rademacher complexity bounds deri…
Generalization BoundsA PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
In this paper, we derive generalization bounds for the two primary classes of graph neural networks (GNNs), namely graph convolutional networks (GCNs) and message passing GNNs (MPGNNs), via a PAC-Bayesian approach. Our r…
Generalization BoundsOn the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry
Understanding the interplay between generalization, expressivity, and the geometry of the input space is a central challenge in graph learning. The expressivity of Graph Neural Networks (GNNs) is typically characterized …
Human Rademacher Complexity
We propose to use Rademacher complexity, originally developed in computational learning theory, as a measure of human learning capacity. Rademacher complexity measures a learners ability to fit random data, and can be u…
Generalization BoundsLearning Theory