Personalized Reward Learning with Interaction-Grounded Learning (IGL)
This addresses the challenge of diverse user communication modalities in recommender systems, offering a personalized approach rather than incremental improvements.
The paper tackles the problem of recommender systems relying on fixed implicit feedback signals by proposing Interaction-Grounded Learning (IGL) to learn personalized reward functions for different users, demonstrating success in simulations and real-world production traces.
In an era of countless content offerings, recommender systems alleviate information overload by providing users with personalized content suggestions. Due to the scarcity of explicit user feedback, modern recommender systems typically optimize for the same fixed combination of implicit feedback signals across all users. However, this approach disregards a growing body of work highlighting that (i) implicit signals can be used by users in diverse ways, signaling anything from satisfaction to active dislike, and (ii) different users communicate preferences in different ways. We propose applying the recent Interaction Grounded Learning (IGL) paradigm to address the challenge of learning representations of diverse user communication modalities. Rather than requiring a fixed, human-designed reward function, IGL is able to learn personalized reward functions for different users and then optimize directly for the latent user satisfaction. We demonstrate the success of IGL with experiments using simulations as well as with real-world production traces.