# Predictive variational autoencoder for learning robust representations of time-series data

arXiv: https://arxiv.org/abs/2312.06932 · HTML: https://mlsanity.com/paper/2312.06932/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Benign Overfitting in Linear Regression](https://mlsanity.com/paper/1906.11300/) (2019)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Variational Autoencoders and Nonlinear ICA: A Unifying Framework](https://mlsanity.com/paper/1907.04809/) (2019)
- [Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding](https://mlsanity.com/paper/2007.10930/) (2020)
- [Learnable latent embeddings for joint behavioral and neural analysis](https://mlsanity.com/paper/2204.00673/) (2022)
- [PixelVAE: A Latent Variable Model for Natural Images](https://mlsanity.com/paper/1611.05013/) (2016)
- [Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity](https://mlsanity.com/paper/2109.04463/) (2021)
- [Consistency Regularization for Variational Auto-Encoders](https://mlsanity.com/paper/2105.14859/) (2021)
- [Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE](https://mlsanity.com/paper/2011.04798/) (2020)
- [Unsupervised Model Selection for Variational Disentangled Representation Learning](https://mlsanity.com/paper/1905.12614/) (2019)
- [Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction](https://mlsanity.com/paper/2102.10106/) (2021)
- [Enabling hyperparameter optimization in sequential autoencoders for spiking neural data](https://mlsanity.com/paper/1908.07896/) (2019)
- [Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity](https://mlsanity.com/paper/2111.02338/) (2021)
- [Expressive architectures enhance interpretability of dynamics-based neural population models](https://mlsanity.com/paper/2212.03771/) (2022)
- [Brain-like representational straightening of natural movies in robust feedforward neural networks](https://mlsanity.com/paper/2308.13870/) (2023)

## Built on by (most cited first, 1 of 1)

- [Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors](https://mlsanity.com/paper/2410.16136/) (2024)

## Abstract (arXiv)

Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in the data rather than true underlying features, rendering such representations unsuitable for scientific interpretation. Existing solutions to this problem involve introducing additional measured variables or data augmentations specific to a particular data type. We propose a VAE architecture that predicts the next point in time and show that it mitigates the learning of spurious features. In addition, we introduce a model selection metric based on smoothness over time in the latent space. We show that together these two constraints on VAEs to be smooth over time produce robust latent representations and faithfully recover latent factors on synthetic datasets.