mlsanityData to 14 Oct 2026

Graph Neural Network and Transformer Integration for Unsupervised System Anomaly Discovery

arXiv 2508.09401 ↗First posted 13 Aug 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

This study proposes an unsupervised anomaly detection method for distributed backend service systems, addressing practical challenges such as complex structural dependencies, diverse behavioral evolution, and the absence of labeled data. The method constructs a dynamic graph based on service invocation relationships and applies graph convolution to extract high-order structural representations from multi-hop topologies. A Transformer is used to model the temporal behavior of each node, capturing long-term dependencies and local fluctuations. During the feature fusion stage, a learnable joint embedding mechanism integrates structural and behavioral representations into a unified anomaly vector. A nonlinear mapping is then applied to compute anomaly scores, enabling an end-to-end detection process without supervision. Experiments on real-world cloud monitoring data include sensitivity analyses across different graph depths, sequence lengths, and data perturbations. Results show that the proposed method outperforms existing models on several key metrics, demonstrating stronger expressiveness and stability in capturing anomaly propagation paths and modeling dynamic behavior sequences, with high potential for practical deployment.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 15 of its 23 references that are in the map. First posted on arXiv 13 Aug 2025.

Builds on

15 of 23 references.

References · 15

  1. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  2. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
  3. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
  4. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 167
  5. 2019Time-Series Anomaly Detection Service at Microsoftcited by 165
  6. 2017Generative Adversarial Active Learningcited by 70
  7. 2018Generative Adversarial Active Learning for Unsupervised Outlier Detectioncited by 65
  8. 2023MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detectioncited by 26
  9. 2025Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scalingcited by 10
  10. 2023Graph Neural Networks based Log Anomaly Detection and Explanationcited by 8
  11. 2025Clinical NLP with Attention-Based Deep Learning for Multi-Disease Predictioncited by 7
  12. 2025Capsule Network-Based Semantic Intent Modeling for Human-Computer Interactioncited by 5
3 more
  1. 2025Collaborative Distillation Strategies for Parameter-Efficient Language Model Deploymentcited by 5
  2. 2025Time-Series Learning for Proactive Fault Prediction in Distributed Systems with Deep Neural Structurescited by 4
  3. 2025Behavioral Anomaly Detection in Distributed Systems via Federated Contrastive Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025Multi-Objective Adaptive Rate Limiting in Microservices Using Deep Reinforcement Learningcited by 5
  2. 2025Dynamic Topic Evolution with Temporal Decay and Attention in Large Language Modelscited by 3
  3. 2025Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networkscited by 1
  4. 2025Dynamic Anomaly Identification in Accounting Transactions via Multi-Head Self-Attention Networkscited by 1