Interpretable Deep Representation Learning from Temporal Multi-view Data
This work addresses the need for interpretable deep representation learning in scientific domains like video surveillance, genomics, and finance, but it appears incremental as it combines existing methods (VAE and RNN) for a known bottleneck.
The authors tackled the problem of integrating multi-view temporal data with time-dependent heterogeneous properties by proposing a generative model based on variational autoencoder and recurrent neural network to infer latent dynamics, demonstrating effectiveness and interpretability on three datasets.
In many scientific problems such as video surveillance, modern genomics, and finance, data are often collected from diverse measurements across time that exhibit time-dependent heterogeneous properties. Thus, it is important to not only integrate data from multiple sources (called multi-view data), but also to incorporate time dependency for deep understanding of the underlying system. We propose a generative model based on variational autoencoder and a recurrent neural network to infer the latent dynamics for multi-view temporal data. This approach allows us to identify the disentangled latent embeddings across views while accounting for the time factor. We invoke our proposed model for analyzing three datasets on which we demonstrate the effectiveness and the interpretability of the model.