Variation Control and Evaluation for Generative SlateRecommendations

TL;DR

This paper addresses the challenge of generating diverse and accurate slate recommendations by introducing variation metrics and perturbation techniques to improve generative models, balancing diversity and relevance.

Contribution

It proposes a novel evaluation method and a perturbation-based approach to enhance diversity in generative slate recommendation models, overcoming overfitting and item concentration issues.

Findings

Variation metrics effectively estimate model stochasticity.

Perturbation expands the 'elbow' region for balanced diversity and accuracy.

Separation of pivot selection and generation improves variance without losing accuracy.

Abstract

Slate recommendation generates a list of items as a whole instead of ranking each item individually, so as to better model the intra-list positional biases and item relations. In order to deal with the enormous combinatorial space of slates, recent work considers a generative solution so that a slate distribution can be directly modeled. However, we observe that such approaches -- despite their proved effectiveness in computer vision -- suffer from a trade-off dilemma in recommender systems: when focusing on reconstruction, they easily over-fit the data and hardly generate satisfactory recommendations; on the other hand, when focusing on satisfying the user interests, they get trapped in a few items and fail to cover the item variation in slates. In this paper, we propose to enhance the accuracy-based evaluation with slate variation metrics to estimate the stochastic behavior of generative models. We illustrate that instead of reaching to one of the two undesirable extreme cases in the dilemma, a valid generative solution resides in a narrow "elbow" region in between. And we show that item perturbation can enforce slate variation and mitigate the over-concentration of generated slates, which expand the "elbow" performance to an easy-to-find region. We further propose to separate a pivot selection phase from the generation process so that the model can apply perturbation before generation. Empirical results show that this simple modification can provide even better variance with the same level of accuracy compared to post-generation perturbation methods.