# Autoencoder Trees

arXiv: https://arxiv.org/abs/1409.7461 · HTML: https://mlsanity.com/paper/1409.7461/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2014.

## Built on by (most cited first, 6 of 6)

- [TAS-NIR: A VIS+NIR Dataset for Fine-grained Semantic Segmentation in Unstructured Outdoor Environments](https://mlsanity.com/paper/2212.09368/) (2022)
- [Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings](https://mlsanity.com/paper/2511.06961/) (2025)
- [Taxonomic Networks: A Representation for Neuro-Symbolic Pairing](https://mlsanity.com/paper/2505.24601/) (2025)
- [Transition Matrix Representation of Trees with Transposed Convolutions](https://mlsanity.com/paper/2202.10677/) (2022)
- [Chains of Autoreplicative Random Forests for missing value imputation in high-dimensional datasets](https://mlsanity.com/paper/2301.00595/) (2023)
- [OF-AE: Oblique Forest AutoEncoders](https://mlsanity.com/paper/2301.00880/) (2023)

## Abstract (arXiv)

We discuss an autoencoder model in which the encoding and decoding functions are implemented by decision trees. We use the soft decision tree where internal nodes realize soft multivariate splits given by a gating function and the overall output is the average of all leaves weighted by the gating values on their path. The encoder tree takes the input and generates a lower dimensional representation in the leaves and the decoder tree takes this and reconstructs the original input. Exploiting the continuity of the trees, autoencoder trees are trained with stochastic gradient descent. On handwritten digit and news data, we see that the autoencoder trees yield good reconstruction error compared to traditional autoencoder perceptrons. We also see that the autoencoder tree captures hierarchical representations at different granularities of the data on its different levels and the leaves capture the localities in the input space.