Semi-Supervised Learning via Compact Latent Space Clustering

TL;DR

This paper introduces a new semi-supervised learning method that uses a graph-based cost function to encourage compact clustering in the latent space, improving class separation and leveraging unlabeled data effectively.

Contribution

It proposes a novel cost function that dynamically constructs a graph over embeddings and uses label propagation to regularize the latent space without altering network architecture.

Findings

Achieves promising results on three benchmark datasets.

Combines graph regularization with efficient inference.

Does not require modifications to existing network architectures.

Abstract

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.