Using Local Spectral Methods to Robustify Graph-Based Learning Algorithms.
David F. GleichMichael W. MahoneyPublished in: KDD (2015)
Keyphrases
- spectral methods
- learning algorithm
- spectral analysis
- normalized cut
- graph construction
- manifold learning
- random walk
- spectral clustering
- graph partitioning
- semi supervised
- active learning
- learning problems
- data mining applications
- training data
- machine learning
- subspace learning
- graph model
- supervised learning
- multi label
- learning tasks
- graph clustering
- eigendecomposition
- semi supervised learning
- text classification
- image segmentation
- mean shift
- unlabeled data
- k nearest neighbor
- model selection
- dimensionality reduction
- nearest neighbor