Semi-Supervised Learning using Siamese Networks
This addresses the challenge of training neural networks effectively in semi-supervised settings where labeled data is scarce, but it appears incremental as it builds on existing self-training and embedding techniques.
The paper tackles the problem of semi-supervised learning with limited labeled data by proposing a new training method using Siamese networks to learn discriminative embeddings, which are then used to iteratively label unlabeled instances via a nearest-neighbor classifier and retrain the network, resulting in an empirical study of this approach.
Neural networks have been successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are more difficult to train successfully for semi-supervised problems where small amounts of labeled instances are available along with a large number of unlabeled instances. This work explores a new training method for semi-supervised learning that is based on similarity function learning using a Siamese network to obtain a suitable embedding. The learned representations are discriminative in Euclidean space, and hence can be used for labeling unlabeled instances using a nearest-neighbor classifier. Confident predictions of unlabeled instances are used as true labels for retraining the Siamese network on the expanded training set. This process is applied iteratively. We perform an empirical study of this iterative self-training algorithm. For improving unlabeled predictions, local learning with global consistency [22] is also evaluated.