mlsanityData to 14 Oct 2026

Towards Foundation Auto-Encoders for Time-Series Anomaly Detection

arXiv 2507.01875 ↗First posted 2 Jul 2025cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We investigate a novel approach to time-series modeling, inspired by the successes of large pretrained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series data, based on Variational Auto-Encoders (VAEs). By foundation, we mean a model pretrained on massive amounts of time-series data which can learn complex temporal patterns useful for accurate modeling, forecasting, and detection of anomalies on previously unseen datasets. FAE leverages VAEs and Dilated Convolutional Neural Networks (DCNNs) to build a generic model for univariate time-series modeling, which could eventually perform properly in out-of-the-box, zero-shot anomaly detection applications. We introduce the main concepts of FAE, and present preliminary results in different multi-dimensional time-series datasets from various domains, including a real dataset from an operational mobile ISP, and the well known KDD 2021 Anomaly Detection dataset.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 2 Jul 2025.

Builds on

19 of 39 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  4. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  5. 2019An Introduction to Variational Autoencoderscited by 1,000
  6. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  7. 2016Tutorial on Variational Autoencoderscited by 409
  8. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  9. 2016Adversarial Feature Learningcited by 350
  10. 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
  11. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 172
  12. 2018Efficient GAN-Based Anomaly Detectioncited by 122
7 more
  1. 2017Improved Variational Autoencoders for Text Modeling using Dilated Convolutionscited by 81
  2. 2018Gaussian Process Prior Variational Autoencoderscited by 72
  3. 2014Learning Stochastic Recurrent Networkscited by 60
  4. 2020TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networkscited by 55
  5. 2020Longitudinal Variational Autoencodercited by 25
  6. 2017Variational Bi-LSTMscited by 3
  7. 2020On the Usage of Generative Models for Network Anomaly Detection in Multivariate Time-Seriescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Towards One-for-All Anomaly Detection for Tabular Datacited by 6