Is Meta-Learning the Right Approach for the Cold-Start Problem in Recommender Systems?

TL;DR

This paper demonstrates that traditional deep learning models and simple modular approaches can match or outperform meta-learning techniques in cold-start recommender system scenarios, challenging the current research focus.

Contribution

It shows that standard deep learning models, when properly tuned, can achieve comparable results to meta-learning methods for cold-start problems, offering more practical solutions.

Findings

Standard models perform as well as meta-learning models on benchmarks.

Simple modular approaches are effective and easier to deploy.

Meta-learning techniques may not be necessary for cold-start recommender systems.

Abstract

Recommender systems have become fundamental building blocks of modern online products and services, and have a substantial impact on user experience. In the past few years, deep learning methods have attracted a lot of research, and are now heavily used in modern real-world recommender systems. Nevertheless, dealing with recommendations in the cold-start setting, e.g., when a user has done limited interactions in the system, is a problem that remains far from solved. Meta-learning techniques, and in particular optimization-based meta-learning, have recently become the most popular approaches in the academic research literature for tackling the cold-start problem in deep learning models for recommender systems. However, current meta-learning approaches are not practical for real-world recommender systems, which have billions of users and items, and strict latency requirements. In this paper we show that it is possible to obtaining similar, or higher, performance on commonly used benchmarks for the cold-start problem without using meta-learning techniques. In more detail, we show that, when tuned correctly, standard and widely adopted deep learning models perform just as well as newer meta-learning models. We further show that an extremely simple modular approach using common representation learning techniques, can perform comparably to meta-learning techniques specifically designed for the cold-start setting while being much more easily deployable in real-world applications.