# Training Deep AutoEncoders for Collaborative Filtering

arXiv: https://arxiv.org/abs/1708.01715 · HTML: https://mlsanity.com/paper/1708.01715/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2017.

## Built on by (most cited first, 10 of 10)

- [Torch.fx: Practical Program Capture and Transformation for Deep Learning in Python](https://mlsanity.com/paper/2112.08429/) (2021)
- [Sheaf4Rec: Sheaf Neural Networks for Graph-based Recommender Systems](https://mlsanity.com/paper/2304.09097/) (2023)
- [Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge Distillation](https://mlsanity.com/paper/2310.18119/) (2023)
- [TorchBench: Benchmarking PyTorch with High API Surface Coverage](https://mlsanity.com/paper/2304.14226/) (2023)
- [RikoNet: A Novel Anime Recommendation Engine](https://mlsanity.com/paper/2106.12970/) (2021)
- [depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers](https://mlsanity.com/paper/2403.13839/) (2024)
- [Decentralized Multi-Target Cross-Domain Recommendation for Multi-Organization Collaborations](https://mlsanity.com/paper/2110.13340/) (2021)
- [A cross-domain recommender system using deep coupled autoencoders](https://mlsanity.com/paper/2112.07617/) (2021)
- [The effectiveness of factorization and similarity blending](https://mlsanity.com/paper/2209.13011/) (2022)
- [Enhancing the conformal predictability of context-aware recommendation systems by using Deep Autoencoders](https://mlsanity.com/paper/2412.12110/) (2024)

## Abstract (arXiv)

This paper proposes a novel model for the rating prediction task in recommender systems which significantly outperforms previous state-of-the art models on a time-split Netflix data set. Our model is based on deep autoencoder with 6 layers and is trained end-to-end without any layer-wise pre-training. We empirically demonstrate that: a) deep autoencoder models generalize much better than the shallow ones, b) non-linear activation functions with negative parts are crucial for training deep models, and c) heavy use of regularization techniques such as dropout is necessary to prevent over-fiting. We also propose a new training algorithm based on iterative output re-feeding to overcome natural sparseness of collaborate filtering. The new algorithm significantly speeds up training and improves model performance. Our code is available at https://github.com/NVIDIA/DeepRecommender