Lu-An Dong

Information-Bottlenecked Variational Autoencoder for Top-N Recommendation via Gating Mechanism

Generative models for top- \(N\) recommendation have garnered significant attention, with Variational Autoencoder (VAE) emerging as a promising approach for modeling user preferences. Yet, traditional VAE-based models encounter two major challenges: simplistic priors may cause posterior collapse, resulting in ineffecti...