Learning by coincidence: Siamese networks and common variable learning

We consider the statistical problem of learning a common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach is useful in particular in exploratory, data-driven applications, where neither a model nor label information is available. In recent years, many researchers have successfully applied Siamese neural networks to obtain an embedding of data which corresponds to a “semantic similarity”. We present an interpretation of this “semantic similarity” as learning of equivalence classes. We demonstrate the ability of Siamese networks to learn common variability in a range of experiments on synthetic and real-world data, and demonstrate the potential of Siamese networks to provide new leads for data-driven research through unsupervised learning in cancer data.