Unsupervised Selective Manifold Regularized Matrix Factorization
Preprint
Abstract
Manifold regularization methods for matrix factorization rely on the cluster assumption, whereby the neighborhood structure of data in the input space is preserved in the factorization space. We argue that using the k-neighborhoods of all data points as regularization constraints can negatively affect the quality of the factorization, and propose an unsupervised and selective regularized matrix factorization algorithm to tackle this problem. Our approach jointly learns a sparse set of representatives and their neighbor affinities, and the data factorization. We further propose a fast approximation of our approach by relaxing the selectivity constraints on the data. Our proposed algorithms are competitive against baselines and state-of-the-art manifold regularization and clustering algorithms.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Adaptive Projected Matrix Factorization method for data clusteringNeurocomputing, 2018
- Robust Structured Nonnegative Matrix Factorization for Image RepresentationIEEE Transactions on Neural Networks and Learning Systems, 2017
- Multi-view clustering via multi-manifold regularized non-negative matrix factorizationNeural Networks, 2017
- Image clustering by hyper-graph regularized non-negative matrix factorizationNeurocomputing, 2014
- Constrained Nonnegative Matrix Factorization for Image RepresentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Graph Regularized Nonnegative Matrix Factorization for Data RepresentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- CUR matrix decompositions for improved data analysisProceedings of the National Academy of Sciences, 2009
- SVD based initialization: A head start for nonnegative matrix factorizationPattern Recognition, 2008
- Sparse non-negative matrix factorizations via alternating non-negativity-constrained least squares for microarray data analysisBioinformatics, 2007
- Rank revealing QR factorizationsLinear Algebra and its Applications, 1987