CSI Clustering with Variational Autoencoding
This work addresses a domain-specific problem in wireless communications engineering for tasks like direction of arrival estimation, but it is incremental as it applies an existing method (VAE) to a new data type with a specific modification.
The paper tackled the problem of grouping unlabeled channel state information by model order using a variational autoencoder in an unsupervised manner, and found that using a more flexible likelihood model in the decoder is crucial for effective clustering, validated on simulated 3GPP channel data.
The model order of a wireless channel plays an important role for a variety of applications in communications engineering, e.g., it represents the number of resolvable incident wavefronts with non-negligible power incident from a transmitter to a receiver. Areas such as direction of arrival estimation leverage the model order to analyze the multipath components of channel state information. In this work, we propose to use a variational autoencoder to group unlabeled channel state information with respect to the model order in the variational autoencoder latent space in an unsupervised manner. We validate our approach with simulated 3GPP channel data. Our results suggest that, in order to learn an appropriate clustering, it is crucial to use a more flexible likelihood model for the variational autoencoder decoder than it is usually the case in standard applications.