Semi-Supervised Learning via Compact Latent Space Clustering
This work addresses the challenge of effectively using unlabeled data in neural networks for semi-supervised learning, offering an incremental improvement with a method that can be easily applied to existing architectures.
The paper tackles the problem of semi-supervised learning by introducing a cost function that encourages compact clustering in the latent space to improve class separation, achieving promising results compared to state-of-the-art methods on three benchmarks.
We present a novel cost function for semi-supervised 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.