LEFT: Learnable fusion of tri-view tokens for unsupervised time series anomaly detection

Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2026

Abstract

As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of annotations. A key challenge in unsupervised TSAD is that many anomalies are too subtle to exhibit detectable deviation in any single view (e.g., time domain), and instead manifest as inconsistencies across multiple views like time, frequency, and a mixture of resolutions. However, most cross-view methods rely on feature or score fusion and do not enforce analysis–synthesis consistency, meaning the frequency branch is not required to reconstruct the time signal through an inverse transform, and vice versa. In this paper, we present Learnable Fusion of Tri-view Tokens (LEFT), a unified unsupervised TSAD framework that models anomalies as inconsistencies across complementary representations. LEFT learns feature tokens from three views of the same input time series: frequency domain tokens that embed periodicity information, time domain tokens that capture local dynamics, and multi-scale tokens that learn abnormal patterns at varying time series granularities. By learning a set of adaptive Nyquist-constrained spectral filters, the original time series is rescaled into multiple resolutions and then encoded, allowing these multi-scale tokens to complement the extracted frequency and time domain information. When generating the fused representation, we introduce a novel objective that reconstructs fine-grained targets from coarser multi-scale structure, and put forward an innovative time-frequency cycle consistency constraint to explicitly regularize cross-view agreement. As cross-view agreement is explicitly regularized during training, LEFT can adopt lightweight tri-view encoders while maintaining effective coordination among the three views. Experiments on real-world benchmarks show that LEFT achieves the best performance among the compared baselines under the reported evaluation metrics, while using over 6× fewer FLOPs and achieving about 8× faster training. Code is available at https://github.com/DezhengWang/Left.git

Keywords

Time Series Anomaly Detection, Unsupervised Learning, Crossview Consistency, Tri-view Tokenization, Learnable Filterbank

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

KDD '26: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, Jeju Island, South Korea, August 9-13

First Page

4800

Last Page

4811

Identifier

10.1145/3770855.3818044

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3770855.3818044

This document is currently not available here.

Share

COinS