Fourier Latent Transformer for Anomaly Signal with High-Frequency Reconstruction

Abstract

Anomaly-related applications play a crucial role in real-world systems. However, developing effective solutions remains challenging, particularly due to missing data caused by system errors during anomaly events. Several approaches have been proposed to address this issue, including statistical methods, autoencoders, and deep learning models such as Transformers and Latent Transformers. Despite their potential, these methods often struggle to preserve high-frequency signal characteristics or require extensive training time and computational resources. To overcome these challenges, this paper proposes the Fourier Latent Transformer for Anomaly Signal with High Frequency Reconstruction. The method integrates Fourier positional encoding, which enhances the model’s ability to retain high-frequency components, with a Latent Transformer architecture that reduces the need for computational resources and shortens training time. This approach not only effectively reconstructs missing highfrequency anomaly signals, but also improves overall training efficiency. Experimental results on real-world datasets show that the proposed method tremendously reduces error in anomaly data imputation, while maintaining training time comparable to baseline models.