# Neural Collaborative Filtering vs. Matrix Factorization Revisited

arXiv: https://arxiv.org/abs/2005.09683 · HTML: https://mlsanity.com/paper/2005.09683/

## Key facts

- Cited by 123 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2020.

## Built on by (most cited first, 30 of 123)

- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [The Benchmark Lottery](https://mlsanity.com/paper/2107.07002/) (2021)
- [Knowledge Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2205.00976/) (2022)
- [A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation](https://mlsanity.com/paper/2104.13030/) (2021)
- [Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations](https://mlsanity.com/paper/2306.08121/) (2023)
- [How Powerful is Graph Convolution for Recommendation?](https://mlsanity.com/paper/2108.07567/) (2021)
- [Deep Learning for Click-Through Rate Estimation](https://mlsanity.com/paper/2104.10584/) (2021)
- [Self-Supervised Hypergraph Transformer for Recommender Systems](https://mlsanity.com/paper/2207.14338/) (2022)
- [Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation](https://mlsanity.com/paper/2203.11491/) (2022)
- [On the Embedding Collapse when Scaling up Recommendation Models](https://mlsanity.com/paper/2310.04400/) (2023)
- [Revisiting the Performance of iALS on Item Recommendation Benchmarks](https://mlsanity.com/paper/2110.14037/) (2021)
- [Infinite Recommendation Networks: A Data-Centric Approach](https://mlsanity.com/paper/2206.02626/) (2022)
- [Evaluating ChatGPT as a Recommender System: A Rigorous Approach](https://mlsanity.com/paper/2309.03613/) (2023)
- [Item Recommendation from Implicit Feedback](https://mlsanity.com/paper/2101.08769/) (2021)
- [SSLRec: A Self-Supervised Learning Framework for Recommendation](https://mlsanity.com/paper/2308.05697/) (2023)
- [Learning Robust Recommenders through Cross-Model Agreement](https://mlsanity.com/paper/2105.09605/) (2021)
- [Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling](https://mlsanity.com/paper/2206.11549/) (2022)
- [Revisiting Neural Retrieval on Accelerators](https://mlsanity.com/paper/2306.04039/) (2023)
- [Improved Global Guarantees for the Nonconvex Burer--Monteiro Factorization via Rank Overparameterization](https://mlsanity.com/paper/2207.01789/) (2022)
- [On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-n Recommendation](https://mlsanity.com/paper/2307.15053/) (2023)
- [Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendation](https://mlsanity.com/paper/2311.18213/) (2023)
- [Robust Collaborative Filtering to Popularity Distribution Shift](https://mlsanity.com/paper/2310.10696/) (2023)
- [Revisiting Neighborhood-based Link Prediction for Collaborative Filtering](https://mlsanity.com/paper/2203.15789/) (2022)
- [MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering](https://mlsanity.com/paper/2204.02338/) (2022)
- [Link Prediction with Non-Contrastive Learning](https://mlsanity.com/paper/2211.14394/) (2022)
- [TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systems](https://mlsanity.com/paper/2308.14355/) (2023)
- [Recommendation Fairness: From Static to Dynamic](https://mlsanity.com/paper/2109.03150/) (2021)
- [Temporal Interest Network for User Response Prediction](https://mlsanity.com/paper/2308.08487/) (2023)
- [Improved Diversity-Promoting Collaborative Metric Learning for Recommendation](https://mlsanity.com/paper/2409.01012/) (2024)

## Abstract (arXiv)

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.