# Neural Network Matrix Factorization

arXiv: https://arxiv.org/abs/1511.06443 · HTML: https://mlsanity.com/paper/1511.06443/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 26 of 26)

- [MQBench: Towards Reproducible and Deployable Model Quantization Benchmark](https://mlsanity.com/paper/2111.03759/) (2021)
- [Recent Developments in Recommender Systems: A Survey](https://mlsanity.com/paper/2306.12680/) (2023)
- [A Neural Matrix Decomposition Recommender System Model based on the Multimodal Large Language Model](https://mlsanity.com/paper/2407.08942/) (2024)
- [Inductive Matrix Completion Using Graph Autoencoder](https://mlsanity.com/paper/2108.11124/) (2021)
- [Efficient Document Ranking with Learnable Late Interactions](https://mlsanity.com/paper/2406.17968/) (2024)
- [Causal Lifting and Link Prediction](https://mlsanity.com/paper/2302.01198/) (2023)
- [Efflex: Efficient and Flexible Pipeline for Spatio-Temporal Trajectory Graph Modeling and Representation Learning](https://mlsanity.com/paper/2404.12400/) (2024)
- [PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models](https://mlsanity.com/paper/2412.07268/) (2024)
- [LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems](https://mlsanity.com/paper/2505.13528/) (2025)
- [Parallel Neurosymbolic Integration with Concordia](https://mlsanity.com/paper/2306.00480/) (2023)
- [Advancing Cultural Inclusivity: Optimizing Embedding Spaces for Balanced Music Recommendations](https://mlsanity.com/paper/2405.17607/) (2024)
- [User Embedding based Neighborhood Aggregation Method for Inductive Recommendation](https://mlsanity.com/paper/2102.07575/) (2021)
- [Learning Complex Users' Preferences for Recommender Systems](https://mlsanity.com/paper/2107.01529/) (2021)
- [Neural Network Approximation of Continuous Functions in High Dimensions with Applications to Inverse Problems](https://mlsanity.com/paper/2208.13305/) (2022)
- [Geometric Collaborative Filtering with Convergence](https://mlsanity.com/paper/2410.03064/) (2024)
- [Multi-Channel Hypergraph Contrastive Learning for Matrix Completion](https://mlsanity.com/paper/2411.01376/) (2024)
- [TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization](https://mlsanity.com/paper/2412.01488/) (2024)
- [Conv4Rec: A 1-by-1 Convolutional AutoEncoder for User Profiling through Joint Analysis of Implicit and Explicit Feedbacks](https://mlsanity.com/paper/2509.07499/) (2025)
- [UserReg: A Simple but Strong Model for Rating Prediction](https://mlsanity.com/paper/2102.07601/) (2021)
- [SUPER-Rec: SUrrounding Position-Enhanced Representation for Recommendation](https://mlsanity.com/paper/2209.04154/) (2022)
- [Self Similarity Matrix based CNN Filter Pruning](https://mlsanity.com/paper/2211.01814/) (2022)
- [Ae2I: A Double Autoencoder for Imputation of Missing Values](https://mlsanity.com/paper/2301.06633/) (2023)
- [A Distance Metric Learning Model Based On Variational Information Bottleneck](https://mlsanity.com/paper/2403.02794/) (2024)
- [Evaluation of data driven low-rank matrix factorization for accelerated solutions of the Vlasov equation](https://mlsanity.com/paper/2501.04024/) (2024)
- [An Interdisciplinary and Cross-Task Review on Missing Data Imputation](https://mlsanity.com/paper/2511.01196/) (2025)
- [Building a privacy-preserving Federated Recommender system for mobile devices](https://mlsanity.com/paper/2605.22924/) (2026)

## Abstract (arXiv)

Data often comes in the form of an array or matrix. Matrix factorization techniques attempt to recover missing or corrupted entries by assuming that the matrix can be written as the product of two low-rank matrices. In other words, matrix factorization approximates the entries of the matrix by a simple, fixed function---namely, the inner product---acting on the latent feature vectors for the corresponding row and column. Here we consider replacing the inner product by an arbitrary function that we learn from the data at the same time as we learn the latent feature vectors. In particular, we replace the inner product by a multi-layer feed-forward neural network, and learn by alternating between optimizing the network for fixed latent features, and optimizing the latent features for a fixed network. The resulting approach---which we call neural network matrix factorization or NNMF, for short---dominates standard low-rank techniques on a suite of benchmark but is dominated by some recent proposals that take advantage of the graph features. Given the vast range of architectures, activation functions, regularizers, and optimization techniques that could be used within the NNMF framework, it seems likely the true potential of the approach has yet to be reached.