Controllable Recommenders using Deep Generative Models and Disentanglement
This addresses the need for more interactive and controllable recommender systems for users, though it is incremental as it builds on existing deep generative and disentanglement methods.
The paper tackles the problem of enabling fine-grained user control over recommendations by introducing a deep generative model with a disentangled latent space, where each dimension corresponds to an item aspect, allowing users to adjust 'knobs' to meet dynamic preferences. It demonstrates that this approach can produce controlled and personalized recommendations with only a slight reduction in performance on collaborative filtering datasets.
In this paper, we consider controllability as a means to satisfy dynamic preferences of users, enabling them to control recommendations such that their current preference is met. While deep models have shown improved performance for collaborative filtering, they are generally not amenable to fine grained control by a user, leading to the development of methods like deep language critiquing. We propose an alternate view, where instead of keyphrase based critiques, a user is provided 'knobs' in a disentangled latent space, with each knob corresponding to an item aspect. Disentanglement here refers to a latent space where generative factors (here, a preference towards an item category like genre) are captured independently in their respective dimensions, thereby enabling predictable manipulations, otherwise not possible in an entangled space. We propose using a (semi-)supervised disentanglement objective for this purpose, as well as multiple metrics to evaluate the controllability and the degree of personalization of controlled recommendations. We show that by updating the disentangled latent space based on user feedback, and by exploiting the generative nature of the recommender, controlled and personalized recommendations can be produced. Through experiments on two widely used collaborative filtering datasets, we demonstrate that a controllable recommender can be trained with a slight reduction in recommender performance, provided enough supervision is provided. The recommendations produced by these models appear to both conform to a user's current preference and remain personalized.