Semi-supervised learning via compact latent space clustering

Kamnitsas K, Castro DC, Le Folgoc L, Walker I, Tanno R, Rueckert D, Glocker B, Criminisi A, Nori A (2018)

Publication Type: Conference contribution

Publication year: 2018

Publisher: International Machine Learning Society (IMLS)

Book Volume: 6

Pages Range: 3845-3854

Conference Proceedings Title: 35th International Conference on Machine Learning, ICML 2018

Event location: Stockholm, SWE

ISBN: 9781510867963

Abstract

We present a novel cost function for semisupervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation. The key idea is to dynamically create a graph over embeddings of labeled and unlabeled samples of a training batch to capture underlying structure in feature space, and use label propagation to estimate its high and low density regions. We then devise a cost function based on Markov chains on the graph that regularizes the latent space to form a single compact cluster per class, while avoiding to disturb existing clusters during optimization. We evaluate our approach on three benchmarks and compare to state-of-the art with promising results. Our approach combines the benefits of graph-based regularization with efficient, inductive inference, does not require modifications to a network architecture, and can thus be easily applied to existing networks to enable an effective use of unlabeled data.

Involved external institutions

Microsoft Corporation US United States (USA) (US) Imperial College London / The Imperial College of Science, Technology and Medicine GB United Kingdom (GB)

How to cite

APA:

Kamnitsas, K., Castro, D.C., Le Folgoc, L., Walker, I., Tanno, R., Rueckert, D.,... Nori, A. (2018). Semi-supervised learning via compact latent space clustering. In Jennifer Dy, Andreas Krause (Eds.), 35th International Conference on Machine Learning, ICML 2018 (pp. 3845-3854). Stockholm, SWE: International Machine Learning Society (IMLS).

MLA:

Kamnitsas, Konstantinos, et al. "Semi-supervised learning via compact latent space clustering." Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholm, SWE Ed. Jennifer Dy, Andreas Krause, International Machine Learning Society (IMLS), 2018. 3845-3854.

BibTeX: Download