Neural Collaborative Filtering vs. Matrix Factorization Revisited
| Autor: | John Anderson, Li Zhang, Walid Krichene, Steffen Rendle |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Similarity (geometry) Computer science Machine Learning (stat.ML) 02 engineering and technology 010501 environmental sciences Recommender system Machine learning computer.software_genre 01 natural sciences Matrix decomposition Computer Science - Information Retrieval Machine Learning (cs.LG) Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering Collaborative filtering 0105 earth and related environmental sciences Hyperparameter business.industry Dot product Multilayer perceptron Embedding 020201 artificial intelligence & image processing Artificial intelligence business computer Information Retrieval (cs.IR) |
| Zdroj: | RecSys |
| DOI: | 10.48550/arxiv.2005.09683 |
| Popis: | Embedding based models have been the state of the art in collaborative filtering for over a decade. Traditionally, the dot product or higher order equivalents have been used to combine two or more embeddings, e.g., most notably in matrix factorization. In recent years, it was suggested to replace the dot product with a learned similarity e.g. using a multilayer perceptron (MLP). This approach is often referred to as neural collaborative filtering (NCF). In this work, we revisit the experiments of the NCF paper that popularized learned similarities using MLPs. First, we show that with a proper hyperparameter selection, a simple dot product substantially outperforms the proposed learned similarities. Second, while a MLP can in theory approximate any function, we show that it is non-trivial to learn a dot product with an MLP. Finally, we discuss practical issues that arise when applying MLP based similarities and show that MLPs are too costly to use for item recommendation in production environments while dot products allow to apply very efficient retrieval algorithms. We conclude that MLPs should be used with care as embedding combiner and that dot products might be a better default choice. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|