DVE: Dynamic Variational Embeddings with Applications in Recommender Systems
This addresses the challenge of dynamic data in recommender systems, offering a novel method for sequence-aware applications, though it is incremental in building on recurrent neural networks.
The paper tackles the problem of embedding high-dimensional features in dynamic, sequence-aware data by introducing Dynamic Variational Embeddings (DVE), which explicitly model intrinsic and temporal variations, and applies it to recommender systems with an end-to-end neural architecture for link prediction.
Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches mainly focus on static data, which usually lead to unsatisfactory performance in applications involving large changes over time. How to dynamically characterize the variation of the embedded features is still largely unexplored. In this paper, we introduce a dynamic variational embedding (DVE) approach for sequence-aware data based on recent advances in recurrent neural networks. DVE can model the node's intrinsic nature and temporal variation explicitly and simultaneously, which are crucial for exploration. We further apply DVE to sequence-aware recommender systems, and develop an end-to-end neural architecture for link prediction.