2019/11/30 by Maurizio Ferrari Dacrema, Simone Boglio, Paolo Cremonesi +1 · 8 citations
Computer Science · #Advanced Technologies in Various Fields #Machine Learning and Data Classification #Recommender Systems and Techniques #cs.IR #cs.LG #cs.NE
paper · pdf · doi:10.1145/3434185
published as ACM Transactions on Information Systems 39, 2, Article 20 (January 2021), 49 pages · Source code and full results available at: https://github.com/MaurizioFD/RecSys2019_DeepLearning_Evaluation
openalex created_date 2019/11/22 · openalex publication_date 2021/01/06 · arxiv created 2021/01/07 · arxiv updated 2021/01/08 · openalex updated_date 2026/07/30
The design of algorithms that generate personalized ranked item lists is a central topic of research in the field of recommender systems. In the past few years, in particular, approaches based on deep learning (neural) techniques have become dominant in the literature. For all of them, substantial progress over the state-of-the-art is claimed. However, indications exist of certain problems in today's research practice, e.g., with respect to the choice and optimization of the baselines used for comparison, raising questions about the published claims. In order to obtain a better understanding of the actual progress, we have tried to reproduce recent results in the area of neural recommendation approaches based on collaborative filtering. The worrying outcome of the analysis of these recent works-all were published at prestigious scientific conferences between 2015 and 2018-is that 11 out of the 12 reproducible neural approaches can be outperformed by conceptually simple methods, e.g., based on the nearest-neighbor heuristics. None of the computationally complex neural methods was actually consistently better than already existing learning-based techniques, e.g., using matrix factorization or linear models. In our analysis, we discuss common issues in today's research practice, which, despite the many papers that are published on the topic, have apparently led the field to a certain level of stagnation.