Discriminative Clustering with Representation Learning with any Ratio of Labeled to Unlabeled Data
arXiv:1912.12979 · doi:10.1007/s11222-021-10067-x
Abstract
We present a discriminative clustering approach in which the feature representation can be learned from data and moreover leverage labeled data. Representation learning can give a similarity-based clustering method the ability to automatically adapt to an underlying, yet hidden, geometric structure of the data. The proposed approach augments the DIFFRAC method with a representation learning capability, using a gradient-based stochastic training algorithm and an optimal transport algorithm with entropic regularization to perform the cluster assignment step. The resulting method is evaluated on several real datasets when varying the ratio of labeled data to unlabeled data and thereby interpolating between the fully unsupervised regime and the fully supervised regime. The experimental results suggest that the proposed method can learn powerful feature representations even in the fully unsupervised regime and can leverage even small amounts of labeled data to improve the feature representations and to obtain better clusterings of complex datasets.
arXiv commentPublished in Statistics and Computing, 2022
References in corpus (13)
- SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
- Learning Representations by Maximizing Mutual Information Across Views
- Deep Neural Networks as Gaussian Processes
- Deep Clustering for Unsupervised Learning of Visual Features
- Learning with Pseudo-Ensembles
- Unsupervised Learning by Predicting Noise
- Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA
- Computational Optimal Transport
- Gaussian Process Behaviour in Wide Deep Neural Networks
- Putting An End to End-to-End: Gradient-Isolated Learning of Representations
- Weakly-Supervised Alignment of Video With Text
- Fractionally-Supervised Classification
- Robust Discriminative Clustering with Sparse Regularizers