# Ae2I: A Double Autoencoder for Imputation of Missing Values

arXiv: https://arxiv.org/abs/2301.06633 · HTML: https://mlsanity.com/paper/2301.06633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 16 Jan 2023.

## Builds on (most cited first, 11 of 11)

- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [Handling Incomplete Heterogeneous Data using VAEs](https://mlsanity.com/paper/1807.03653/) (2018)
- [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1905.06874/) (2019)
- [Inductive Matrix Completion Based on Graph Neural Networks](https://mlsanity.com/paper/1904.12058/) (2019)
- [Deep Models of Interactions Across Sets](https://mlsanity.com/paper/1803.02879/) (2018)
- [VIGAN: Missing View Imputation with Generative Adversarial Networks](https://mlsanity.com/paper/1708.06724/) (2017)
- [Neural Network Matrix Factorization](https://mlsanity.com/paper/1511.06443/) (2015)
- [A Neural Autoregressive Approach to Collaborative Filtering](https://mlsanity.com/paper/1605.09477/) (2016)
- [Hybrid Recommender System based on Autoencoders](https://mlsanity.com/paper/1606.07659/) (2016)
- [Joint Neural Collaborative Filtering for Recommender Systems](https://mlsanity.com/paper/1907.03459/) (2019)
- [GLocal-K: Global and Local Kernels for Recommender Systems](https://mlsanity.com/paper/2108.12184/) (2021)

## Abstract (arXiv)

The most common strategy of imputing missing values in a table is to study either the column-column relationship or the row-row relationship of the data table, then use the relationship to impute the missing values based on the non-missing values from other columns of the same row, or from the other rows of the same column. This paper introduces a double autoencoder for imputation (Ae2I) that simultaneously and collaboratively uses both row-row relationship and column-column relationship to impute the missing values. Empirical tests on Movielens 1M dataset demonstrated that Ae2I outperforms the current state-of-the-art models for recommender systems by a significant margin.