Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning
This work addresses the challenge of generating accurate and efficient recommendations for users, but it appears incremental as it adapts existing GAN and imitation learning methods to the recommendation domain.
The paper tackles the problem of improving recommender systems by using energy-based sequence generative adversarial networks (EB-SeqGANs) to model user preferences over time, and it connects this approach to maximum-entropy imitation learning for enhanced interpretability.
Recommender systems aim to find an accurate and efficient mapping from historic data of user-preferred items to a new item that is to be liked by a user. Towards this goal, energy-based sequence generative adversarial nets (EB-SeqGANs) are adopted for recommendation by learning a generative model for the time series of user-preferred items. By recasting the energy function as the feature function, the proposed EB-SeqGANs is interpreted as an instance of maximum-entropy imitation learning.