2006
NeurIPS
NeurIPS 2006
Learning on Graph with Laplacian Regularization
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.
🚀
Conference Pioneer
- NeurIPS 2006
🌱
Topic Pioneer
- Graph Neural Networks
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Mathematics & Optimization
📈
Trend Setter
- Regularization
🧭
Keyword Pioneer
- graph-based learning
🐣
Hot Topic Early Bird
- generalization bound
Authors
Topics
Machine Learning > Core Methods > Classification
Machine Learning > Core Methods > Representation Learning
Machine Learning > Learning Types > Semi-Supervised Learning
Deep Learning > Architectures > Graph Neural Networks
Mathematics & Optimization > Mathematics > Graph Theory
Machine Learning > Core Methods > Graphical Models
Machine Learning > Core Methods > Graph Neural Networks
Deep Learning > Learning Types > Representation Learning
Machine Learning > Learning Types > Regularization
Machine Learning > Optimization & Theory > Generalization
Deep Learning > Optimization & Theory > Regularization