RaCT: Toward Amortized Ranking-Critical Training For Collaborative Filtering

Sam Lobel*, Chunyuan Li*, Jianfeng Gao, Lawrence Carin

Keywords: Collaborative Filtering, Recommender Systems, Actor-Critic, Learned Metrics

TL;DR: We apply the actor-critic methodology from reinforcement learning to collaborative filtering, resulting in improved performance across a variety of latent-variable models

Abstract:

We investigate new methods for training collaborative filtering models based on actor-critic reinforcement learning, to more directly maximize ranking-based objective functions. Specifically, we train a critic network to approximate ranking-based metrics, and then update the actor network to directly optimize against the learned metrics. In contrast to traditional learning-to-rank methods that require re-running the optimization procedure for new lists, our critic-based method amortizes the scoring process with a neural network, and can directly provide the (approximate) ranking scores for new lists.

We demonstrate the actor-critic's ability to significantly improve the performance of a variety of prediction models, and achieve better or comparable performance to a variety of strong baselines on three large-scale datasets.

Code: https://github.com/samlobel/RaCT_CF