Learning on Graph with Laplacian Regularization

Part of Advances in Neural Information Processing Systems 19 (NIPS 2006)

Bibtex Metadata Paper

Authors

Rie Ando, Tong Zhang

Abstract

We consider a general form of transductive learning on graphs with Laplacian regularization, and derive margin-based generalization bounds using appropriate geometric properties of the graph. We use this analysis to obtain a better understanding of the role of normalization of the graph Laplacian matrix as well as the effect of dimension reduction. The results suggest a limitation of the standard degree-based normalization. We propose a remedy from our analysis and demonstrate empirically that the remedy leads to improved classification performance.