Representation-Constrained Autoencoders and an Application to Wireless Positioning
In a number of practical applications that rely on dimensionality reduction, the dataset or measurement process provides valuable side information that can be incorporated when learning low-dimensional embeddings. We propose the inclusion of pairwise representation constraints into autoencoders (AEs) with the goal of promoting application-specific structure. We use synthetic results to show that only a small amount of AE representation constraints are required to substantially improve the local and global neighborhood preserving properties of the learned embeddings. To demonstrate the efficacy of our approach and to illustrate a practical application that naturally provides such representation constraints, we focus on wireless positioning using a recently proposed channel charting framework. We show that representation-constrained AEs recover the global geometry of the learned low-dimensional representations, which enables channel charting to perform approximate positioning without access to global navigation satellite systems or supervised learning methods that rely on extensive measurement campaigns.
PDF Abstract
