Triple:The Interpretable Deep Learning Anomaly Detection Framework based on Trace-Metric-Log of Microservice
The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
Existing anomaly detection approaches based on deep-learning just could simultaneously dig out key information from two dimensions in the traces, metrics or logs. Besides, they just output simple binary result, which ignores the key artificial statement information in the log. In this paper, we propose Triple, an interpretable anomaly detection approach based on deep learning for microservice system. More importantly, Triple aims to help engineers to establish trust in the system decision from key metrics and the artificial statements in logs. Triple leverages graph representation to describe the complicated dependency relationship in the traces with the logs and metrics embedded into the node features. Based on the graph representation, Triple trains a Spatial-Temporal Graph Convolutional Network(STGCN) to capture the key information and generate decision boundary by deep SVDD, which detects the system's anomaly. In addition, we design an interpreter to transfer the simple binary result into a humanly understandable result, including log, metrics and trace, to facilitate engineers' understanding and handling of the incoming incident. Our work has four aims. First, to the best of our knowledge, we are the first to simultaneously apply three data sources to finish anomaly detection in the domain. Second, we design a new anomaly detection method that is an STGCN based on SVDD. Third, we design an interpreter that makes the decision not only a simple binary result. The interpretable result could capture the key artificial statement information in the log and assist engineers in incident troubleshooting. Finally, we design a series experiments to validate our method's effectiveness in the real-world system's dataset. Our results show that Triple consistently achieves improvements over other state-of-the-art models by 11%-65%.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Global frameworks such as AutoMAP [96], DLA [106], and recent graph-based models [107-109] integrate multiple layers of metrics into unified representations for robust detection and diagnosis.”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [108]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 2×
“We leverage Adam [19] to optimize the STGCN’s parameters W , radius R and center c .”
MethodGrad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Veličković, P., Casanova, A., Liò, P., Cucurull, G., Romero, A., & Bengio, Y. (2017) · arXiv (Cornell University) · doi:10.17863/cam.48429 · Cited by 8,657
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
Yu, B., Yin, H., & Zhu, Z. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/505 · Cited by 3,728 · cited 1×
“Then, Triple trains a STGCN based Deep SVDD(Support Vector Data Description) model, which could extracts key information from the unified graph representation and construct a data-enclosing hypersphere in output space [30], [35].”
MethodAttention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting
Guo, S., Lin, Y., Feng, N., Song, C., & Wan, H. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.3301922 · Cited by 3,123 · cited 1×
“ATT originates from graph attention network (GAT) [33] and ASTGCN [17] that learns attention weights for edges in the dependency graph, which we use as a proxy measure of edge importance.”
MethodDeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning
Du, M., Li, F., Zheng, G., & Srikumar, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134015 · Cited by 1,835 · cited 3×
“1) Temporal Block: Although LSTM-based models are effective in time-series analysis for anomaly detection [15], it requires time-consuming iterations, which are slow to respond to dynamic changes.”
BackgroundMethodRuff, L., Vandermeulen, R. A., Görnitz, N., Deecke, L., Siddiqui, S. A., Binder, A., Müller, E., & Kloft, M. (2018) · International Conference on Machine Learning · Cited by 1,719
Drain: an online log parsing approach with fixed depth tree
He, P., Zhu, J., Zheng, Z., & Lyu, M. R. (2017) · 2017 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws.2017.13 · Cited by 943 · cited 1×
“First, we parse the normal history log messages to construct standard template base offline by drain [18].”
MethodGNNExplainer: Generating Explanations for Graph Neural Networks
Ying, R., Bourgeois, D., You, J., Zitnik, M., & Leskovec, J. (2019) · arXiv · doi:10.48550/arxiv.1903.03894 · Cited by 850 · cited 1×
“GNNExplainer [34] learns soft masks for edges and node features to the original graph via element-wise perturbation.”
Background
Research works printed but not linked: 12
- zhang, 2022, Deeptralog Trace-log combined microservice anomaly detection through graph-based deep learning
- 2022, Elasticsearch
- 2019, Hipster-shop
- gan, 0, Seer: Leveraging big data to navigate the complexity of performance debugging in cloud microservices, Proceedings of the fourth international conference on Architectural support for programming languages and operating systems - AS, 19
- 2022, skywalking apache org Apache SkyWalking
- 2022, Prometheus
- 2022, Triple's source code
- 2022, International AIOps Challenge
- 2022, High-quality ubiquitous and portable telemetry to enable effective observability
- 2022, Kubernetes-Production-Grade Container Orchestration
- 2022, Jaeger Open Source End-to-End Distributed Tracing
- 10.1145/3368089.3409672 · DOI
Cited by
Multivocal study on microservice dependencies
Abdelfattah, A. S., Cerny, T., Chy, M. S. H., Uddin, M. A., Perry, S., Brown, C., Goodrich, L., Hurtado, M., Hassan, M., Cai, Y., et al. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112334 · Cited by 12
Gomes, F., Rêgo, P. A. L., & Trinta, F. A. M. (2025) · Computing · doi:10.1007/s00607-025-01540-w · Cited by 22
Kong, H., Li, T., Ge, J., Zhang, L., & Li, L. (2024) · Automated Software Engineering · doi:10.1007/s10515-024-00445-w · Cited by 9
“Ren et al. (2023) utilized three data sources-metrics, traces, and logs-to build a unified graph representation that elucidates complex dependencies among these elements.”
Hrusto, A., Runeson, P., & Ohlsson, M. C. (2024) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1145/3639477.3639712 · Cited by 7
“Logs, as the other significant part of monitoring data, were also of interest for analysis and detecting anomalies, standalone or in combination with metrics [11, 19].”
BackgroundMethodDing, K., Ma, Y., Song, Z., & Bian, K. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3736938 · Cited by 4
“In Figure 2(c), each ST-Residual Block processes the input 𝑋 𝑘 through a TCN [22] to capture temporal dependencies.”
Influential
Metadata
- Authors
- Ren, R., Wang, Y., Liu, F., Li, Z., & Xie, G.
- Affiliations
- Institute of Computing Technology (CN)
- Chinese Academy of Sciences (CN)
- Venue
- 2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS)
- Publisher
- IEEE
- Published
- 2023-06-19
- Pages
- 1-10
- ISSN
- 1548-615X (ISSN-L)
- OpenAlex
- W4385302163
- Cited by
- 16
- References
- 33
- Citations by year
- 2026: 3 · 2025: 9 · 2024: 4
- FWCI
- 4.82
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Workshop on Quality of Service (publishedVersion)
- Funders
- National Key RD Program of China (2022YFB3103000)
- Natural Science Foundation of China (U20A20180,62072437)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- anomaly detection, microservices, explainable deep learning, spatio-temporal graph convolutional network, Deep SVDD, graph representation, decision explanation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Triple:The Interpretable Deep Learning Anomaly Detection Framework based on Trace-Metric-Log of Microservice. https://app.cochat.ai/papers/10.1109/iwqos57198.2023.10188773
- The paper
- Ren, R., Wang, Y., Liu, F., Li, Z., & Xie, G. (2023). Triple:The Interpretable Deep Learning Anomaly Detection Framework based on Trace-Metric-Log of Microservice. 2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS). https://doi.org/10.1109/iwqos57198.2023.10188773
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.