Sahito A., Frank E., Pfahringer B. (2019) Semi-supervised Learning Using Siamese Networks. In: Liu J., Bailey J. (eds) AI 2019: Advances in Artificial Intelligence. AI 2019. Lecture Notes in Computer Science, vol 11919. Springer, Cham
Permanent Research Commons link: https://hdl.handle.net/10289/13356
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  is also evaluated.
This is a post-peer-review, pre-copyedit version of an article published in AI 2019: Advances in Artificial Intelligence. The final authenticated version is available online at https://doi.org/10.1007/978-3-030-35288-2_47