FacGraph: Frequent Anomaly Correlation Graph Mining for Root Cause Diagnose in Micro-Service Architecture
The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
Micro-service architecture is a promising paradigm to develop, deploy and maintain applications using independent and autonomous cloud services. Nowadays, increasingly applications are embracing this model. However, it is difficult and time-consuming to diagnose and identify the actual root cause when anomalies occurs in micro-service architecture due to various factors. This paper introduces a novel framework for anomaly investigation and root cause identification in micro-service architecture. The novelty in our work lies on: (1) Different from existing solutions, in our framework, we propose a frequent pattern mining algorithm on anomaly correlation graph, named FacGraph, to discover root cause services. (2) We leverage breadth first ordered string (BFOS) to reduce the time-consumption of the frequent graph mining (FSM) (3) We further develop a distributed version of FacGraph to improve its paralleled computing efficiency. We evaluate our framework in real production environment IBM Bluemix. Result demonstrate that FacGraph outperforms other methods in diagnosis accuracy and offers a fast identification of root cause service when an anomaly occurs.
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
“Early approaches such as Moni-torRank [129] and FacGraph [130] introduced graph-based ranking to prioritize likely root causes, although these techniques required heavy computation.”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [130]
In the citing paper
“Lin et al. [130] applied the PC algorithm to generate correlation graphs”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [130]
Citations
Cites
Causation, Prediction, and Search
Spirtes, P., Glymour, C., & Scheines, R. (2001) · doi:10.7551/mitpress/1754.001.0001 · Cited by 4,521
Mining frequent patterns without candidate generation
Han, J., Pei, J., & Yin, Y. (2000) · Proceedings of the 2000 ACM SIGMOD international conference on Management of data · doi:10.1145/342009.335372 · Cited by 3,216 · cited 1×
“Many works improve their performance on that basis, see [20-23].”
BackgroundgSpan: graph-based substructure pattern mining
Yan, X., & Han, J. (2003) · 2002 IEEE International Conference on Data Mining, 2002. Proceedings. · doi:10.1109/icdm.2002.1184038 · Cited by 2,013 · cited 1×
“There are lots of methods based on candidate set expansion being proposed [15, 16, 17, 18, 19].”
MethodGraph based anomaly detection and description: a survey
Akoglu, L., Tong, H., & Koutra, D. (2015) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-014-0365-y · Cited by 1,504 · cited 1×
“There are more effective and recent approaches focusing on this problem, see [8, 9, 10].”
BackgroundFrequent pattern mining: current status and future directions
Han, J., Cheng, H., Xin, D., & Yan, X. (2007) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-006-0059-1 · Cited by 1,380 · cited 1×
“of the total set of frequent subgraphs [19, 24, 25].”
BackgroundFault detection and diagnosis in engineering systems
Thomas, P. (2002) · Control Engineering Practice · doi:10.1016/s0967-0661(02)00064-3 · Cited by 1,171
Kuramochi, M., & Karypis, G. (2002) · Proceedings 2001 IEEE International Conference on Data Mining · doi:10.1109/icdm.2001.989534 · Cited by 1,068 · cited 1×
“There are lots of methods based on candidate set expansion being proposed [15, 16, 17, 18, 19].”
MethodAn Apriori-Based Algorithm for Mining Frequent Substructures from Graph Data
Inokuchi, A., Washio, T., & Motoda, H. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45372-5_2 · Cited by 1,039 · cited 1×
“There are lots of methods based on candidate set expansion being proposed [15, 16, 17, 18, 19].”
MethodNewman, S. (2015) · CERN Document Server (European Organization for Nuclear Research) · Cited by 794
Microservices Architecture Enables DevOps: Migration to a Cloud-Native Architecture
Balalaie, A., Heydarnoori, A., & Jamshidi, P. (2016) · IEEE Software · doi:10.1109/ms.2016.64 · Cited by 735 · cited 1×
“Significant research efforts have been devoted to figure out the root cause error of micro-service architecture in the literatures [3, 4].”
BackgroundCloseGraph: mining closed frequent graph patterns
Yan, X., & Han, J. (2003) · Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/956750.956784 · Cited by 635 · cited 2×
“of the total set of frequent subgraphs [19, 24, 25].”
BackgroundMethodEfficient mining of frequent subgraphs in the presence of isomorphism
Huan, J., Wang, W., & Prins, J. (2004) · Third IEEE International Conference on Data Mining · doi:10.1109/icdm.2003.1250974 · Cited by 614 · cited 1×
“There are lots of methods based on candidate set expansion being proposed [15, 16, 17, 18, 19].”
MethodFast algorithms for frequent itemset mining using FP-trees
Grahne, G., & Zhu, J. (2005) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2005.166 · Cited by 549 · cited 1×
“Many works improve their performance on that basis, see [20-23].”
BackgroundA survey of fault localization techniques in computer networks
Steinder, M. Ł., & Sethi, A. S. (2004) · Science of Computer Programming · doi:10.1016/j.scico.2004.01.010 · Cited by 358 · cited 1×
“Significant research efforts have been devoted to figure out the root cause error of micro-service architecture in the literatures [3, 4].”
BackgroundA survey of frequent subgraph mining algorithms
Jiang, C., Coenen, F., & Zito, M. (2013) · The Knowledge Engineering Review · doi:10.1017/s0269888912000331 · Cited by 346 · cited 1×
“The objective of FSM is to extract all the frequent patterns in a given data set [14].”
BackgroundCapturing, indexing, clustering, and retrieving system history
Cohen, I., Zhang, S., Goldszmidt, M., Symons, J., Kelly, T., & Fox, A. (2005) · ACM SIGOPS Operating Systems Review · doi:10.1145/1095809.1095821 · Cited by 280
CloudRanger: Root Cause Identification for Cloud Native Systems
Wang, P., Xu, J., Ma, M., Lin, W., Pan, D., Wang, Y., & Chen, P. (2018) · 2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID) · doi:10.1109/ccgrid.2018.00076 · Cited by 181 · cited 2×
“ServiceRank is a heuristic root cause algorithm based on second-order random walk.”
MethodSelf-citationd-Separation: From Theorems to Algorithms
Geiger, D., Verma, T. S., & Pearl, J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.1505 · Cited by 180 · cited 1×
“For any remaining undirected edge, there direction can be oriented by repeatedly applying the checking rules, see [29] for details.”
BackgroundAnomaly Detection Using Program Control Flow Graph Mining From Execution Logs
Nandi, A., Mandal, A., Atreja, S., Dasgupta, G. B., & Bhattacharya, S. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939712 · Cited by 154 · cited 1×
“Some recent efforts start with mining templates from logs to form a control flow graph [13].”
BackgroundRoot cause detection in a service-oriented architecture
Kim, M., Sumbaly, R., & Shah, S. (2013) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/2494232.2465753 · Cited by 138
CP-Tree: A Tree Structure for Single-Pass Frequent Pattern Mining
Tanbeer, S. K., Ahmed, C. F., Jeong, B.-S., & Lee, Y.-K. (2008) · Springer eBooks · doi:10.1007/978-3-540-68125-0_108 · Cited by 74 · cited 1×
“Many works improve their performance on that basis, see [20-23].”
BackgroundMARGIN: Maximal frequent subgraph mining
Thomas, L. T., Valluri, S. R., & Karlapalem, K. (2010) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/1839490.1839491 · Cited by 73 · cited 1×
“of the total set of frequent subgraphs [19, 24, 25].”
BackgroundMarwede, N., Röhr, M., van Hoorn, A., & Hasselbring, W. (2009) · Euromicro Conference on Software Maintenance and Reengineering (CSMR) · doi:10.1109/csmr.2009.15 · Cited by 64 · cited 1×
“We compare the algorithm in this paper with several benchmark algorithms - ServiceRank [30], Random, TBAC [31] (Timing Behavior Anomaly Correlation) and MonitorRank [32].”
MethodIncremental Frequent Subgraph Mining on Large Evolving Graphs
Abdelhamid, E., Canim, M., Sadoghi, M., Bhattacharjee, B., Chang, Y., & Kalnis, P. (2017) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2017.2743075 · Cited by 62 · cited 1×
“Recent work [26] focuses on a fast incremental approach for continuous frequent subgraph mining on a single large evolving graph.”
BackgroundSucahyo, Y. G., & Gopalan, R. P. (2004) · Cited by 54
Anomaly localization for network data streams with graph joint sparse PCA
Jiang, R., Fei, H., & Huan, J. (2011) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2020408.2020557 · Cited by 47 · cited 1×
“More effective and recent approaches typically focus on knowledge mining based on real-time metrics [6] and system information [7].”
BackgroundVScope: Middleware for Troubleshooting Time-Sensitive Data Center Applications
Wang, C., Rayan, I. A., Eisenhauer, G., Schwan, K., Talwar, V., Wolf, M., & Huneycutt, C. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35170-9_7 · Cited by 39 · cited 1×
“There are more effective and recent approaches focusing on this problem, see [8, 9, 10].”
BackgroundLearning the Dependence Graph of Time Series with Latent FactorsPreprint
Jalali, A., & Sanghavi, S. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1106.1887 · Cited by 38 · cited 1×
“There are more effective and recent approaches focusing on this problem, see [8, 9, 10].”
BackgroundA distributed data streaming algorithm for network-wide traffic anomaly detection
Liu, Y., Zhang, L., & Guan, Y. (2009) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/1639562.1639596 · Cited by 21 · cited 1×
“More effective and recent approaches typically focus on knowledge mining based on real-time metrics [6] and system information [7].”
BackgroundRanking Metric Anomaly in Invariant Networks
Ge, Y., Jiang, G., Ding, M., & Xiong, H. (2014) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/2601436 · Cited by 19 · cited 1×
“mRank and gRank algorithms were proposed for root cause ranking [11].”
Method
Research works printed but not linked: 1
- 10.1145/2494232.2465753 · DOI · Paper page
Cited by
Soldani, J., & Brogi, A. (2023) · ACM Computing Surveys · doi:10.1145/3501297 · Cited by 256
“The other techniques instead determine the possible root causes for anomalies observed with external monitoring tools, by end users, or by application operators [1, 9, 28, 38, 43, 44, 48–50, 55, 56, 62, 63, 69, 84, 96].”
BackgroundMethodInfluentialQiu, J., Du, Q., Yin, K., Zhang, S.-L., & Qian, C. (2020) · Applied Sciences · doi:10.3390/app10062166 · Cited by 96
Detecting anomalies in microservices with execution trace comparison
Meng, L., Ji, F., Sun, Y., & Wang, T. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.040 · Cited by 70
Hao, J., Chen, P., Chen, J., & Li, X. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104107 · Cited by 67
Failure Diagnosis in Microservice Systems: A Comprehensive Survey and Analysis
Zhang, S., Xia, S., Fan, W., Shi, B., Xiong, X., Zhong, Z., Ma, M., Sun, Y., & Pei, D. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3715005 · Cited by 57
Self-citation
Metadata
- Authors
- Lin, W., Ma, M., Pan, D., & Wang, P.
- Affiliations
- Peking University (CN)
- ORCID
- Venue
- 2018 IEEE 37th International Performance Computing and Communications Conference (IPCCC)
- Publisher
- IEEE
- Published
- 2018-11
- Pages
- 1-8
- ISSN
- 1097-2641 (ISSN-L)
- OpenAlex
- W2946651629
- Cited by
- 29
- References
- 30
- Citations by year
- 2026: 4 · 2025: 5 · 2024: 7 · 2023: 3 · 2022: 5 · 2021: 1 · 2020: 4
- FWCI
- 1.03
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Performance, Computing, and Communications Conference (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications
- Physical Sciences › Computer Science › Information Systems › Advanced Database Systems and Queries
- Keywords
- microservices, frequent pattern mining, root cause diagnosis, anomaly investigation, cloud service monitoring
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
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.