Situating Recommender Systems in Practice: Towards Inductive Learning and Incremental Updates

TL;DR

This paper emphasizes the importance of inductive learning and incremental updates in recommender systems to better handle real-world dynamic environments with unseen users and new data.

Contribution

It formalizes the limitations of current static and transductive approaches and advocates for future research in inductive and incremental recommender system methods.

Findings

Highlights the gap between research and practice in recommender systems.

Identifies key challenges in implementing inductive and incremental learning.

Provides best practices and open challenges for future research.

Abstract

With information systems becoming larger scale, recommendation systems are a topic of growing interest in machine learning research and industry. Even though progress on improving model design has been rapid in research, we argue that many advances fail to translate into practice because of two limiting assumptions. First, most approaches focus on a transductive learning setting which cannot handle unseen users or items and second, many existing methods are developed for static settings that cannot incorporate new data as it becomes available. We argue that these are largely impractical assumptions on real-world platforms where new user interactions happen in real time. In this survey paper, we formalize both concepts and contextualize recommender systems work from the last six years. We then discuss why and how future work should move towards inductive learning and incremental updates for recommendation model design and evaluation. In addition, we present best practices and fundamental open challenges for future research.