ML Anthology

Improving Novel Anomaly Detection with Domain-Invariant Latent Representations

Padmaksha Roy, Ming Jin, Himanshu Singhal, Tyler Cody, Kevin Choi
ECML-PKDD 2025 pp. 106-123
doi:10.1007/978-3-032-05962-8_7 /ecmlpkdd/2025/roy2025ecmlpkdd-improving/

Abstract

Zero-day anomaly detection is critical in industrial applications where novel, unforeseen threats can compromise system integrity and safety. Traditional detection systems often fail to identify these unseen anomalies due to their reliance on in-distribution data. Domain generalization addresses this gap by leveraging knowledge from multiple known domains to detect out-of-distribution events. In this work, we introduce a multi-task representation learning technique that fuses information across related domains into a unified latent space. By jointly optimizing classification, reconstruction, and mutual information regularization losses, our method learns a minimal(bottleneck), domain-invariant representation that discards spurious correlations. This latent space decorrelation enhances generalization, enabling the detection of anomalies in unseen domains. Our experimental results demonstrate significant improvements in zero-day or novel anomaly detection across diverse anomaly detection datasets.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Roy et al. "Improving Novel Anomaly Detection with Domain-Invariant Latent Representations." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025. doi:10.1007/978-3-032-05962-8_7

Markdown

[Roy et al. "Improving Novel Anomaly Detection with Domain-Invariant Latent Representations." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025.](https://mlanthology.org/ecmlpkdd/2025/roy2025ecmlpkdd-improving/) doi:10.1007/978-3-032-05962-8_7

BibTeX

@inproceedings{roy2025ecmlpkdd-improving,
  title     = {{Improving Novel Anomaly Detection with Domain-Invariant Latent Representations}},
  author    = {Roy, Padmaksha and Jin, Ming and Singhal, Himanshu and Cody, Tyler and Choi, Kevin},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2025},
  pages     = {106-123},
  doi       = {10.1007/978-3-032-05962-8_7},
  url       = {https://mlanthology.org/ecmlpkdd/2025/roy2025ecmlpkdd-improving/}
}