ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection

2025-09-29

AI Summary

Multivariate time-series anomaly detection in industrial IoT faces challenges including difficulty in modeling spatiotemporal couplings and low sensitivity to discrete anomalies in high-dimensional spaces. To address these, we propose a scattering-aware dual-view representation learning framework. First, we formalize the scattering phenomenon of high-dimensional samples as quantifiable topological features—introducing dual encoders for temporal scattering and topological scattering. Second, we design a contrastive fusion strategy to enhance cross-view consistency: a topological encoder captures graph-structured scattering properties, while a temporal encoder suppresses excessive scattering across adjacent time steps. Third, we jointly optimize mean squared error and conditional mutual information to improve representation discriminability. Our method achieves state-of-the-art performance on multiple benchmark datasets. The source code is publicly available.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Representation Learning for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

One main challenge in time series anomaly detection for industrial IoT lies in the complex spatio-temporal couplings within multivariate data. However, traditional anomaly detection methods focus on modeling spatial or temporal dependencies independently, resulting in suboptimal representation learning and limited sensitivity to anomalous dispersion in high-dimensional spaces. In this work, we conduct an empirical analysis showing that both normal and anomalous samples tend to scatter in high-dimensional space, especially anomalous samples are markedly more dispersed. We formalize this dispersion phenomenon as scattering, quantified by the mean pairwise distance among sample representations, and leverage it as an inductive signal to enhance spatio-temporal anomaly detection. Technically, we propose ScatterAD to model representation scattering across temporal and topological dimensions. ScatterAD incorporates a topological encoder for capturing graph-structured scattering and a temporal encoder for constraining over-scattering through mean squared error minimization between neighboring time steps. We introduce a contrastive fusion mechanism to ensure the complementarity of the learned temporal and topological representations. Additionally, we theoretically show that maximizing the conditional mutual information between temporal and topological views improves cross-view consistency and enhances more discriminative representations. Extensive experiments on multiple public benchmarks show that ScatterAD achieves state-of-the-art performance on multivariate time series anomaly detection. Code is available at this repository: https://github.com/jk-sounds/ScatterAD.

Problem

• Modeling complex spatio-temporal couplings in multivariate industrial IoT data
• Detecting anomalous dispersion patterns in high-dimensional time series
• Enhancing sensitivity to scattering phenomena across temporal and topological dimensions

Innovation

• Models scattering across temporal and topological dimensions
• Uses topological encoder for graph-structured scattering
• Employs contrastive fusion for complementary representations