Sibo Xia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sibo Xia has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Shenglin Zhang
Nankai University, Tianjin, China
9 shared publications - Yongqian Sun
Nankai University, Tianjin, China
9 shared publications - Dan Pei
Tsinghua University, Beijing, China
6 shared publications - Binpeng Shi
Nankai University, Tianjin, China
3 shared publications - Minghua Ma
Microsoft, Redmond, Washington, USA
3 shared publications - Junhua Kuang
Nankai University, Tianjin, China
2 shared publications
Latest Publications
- Open Access
- 31 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Why Transformers? A Comprehensive Overview of Transformers in Artificial Intelligence for IT Operations
AIOps (Artificial Intelligence for IT Operations) has emerged as a key strategy for operating large-scale systems. Meanwhile, the Transformer architecture, renowned for its strong performance and potential, is driving advances in AIOps. However, prior reviews leave gaps in explaining why Transformers trigger a major shift in academia and industry, with limited coverage of multimodal data (logs, metrics, events), insufficient analysis of structural and methodological connections between Transformers and AIOps, fragmented views of capabilities, and a lack of consolidated evaluation strategies. To bridge these gaps, our work decomposes “Why Transformers” into three questions. First, we review what roles Transformers assume in AIOps across 70 representative papers, using a structured taxonomy that proceeds sequentially from data to targets, principles, and approaches, which present an evolutionary trajectory of role changes. Then, to explain why Transformers excel, we introduce a capability framework comprising two basic and four advanced capabilities. As for how to evaluate Transformers in AIOps, we consolidate evaluation resources and strategies, including offline datasets, standardized questions, and real-time simulations. Furthermore, probable best practices are distilled, offering actionable guidance for real-world adoption. These explorations aim to clarify the internal rationale and unlock the practical value of Transformers in AIOps.
- 31 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Open AccessWhy Transformers? A Comprehensive Overview of Transformers in Artificial Intelligence for IT Operations
AIOps (Artificial Intelligence for IT Operations) has emerged as a key strategy for operating large-scale systems. Meanwhile, the Transformer architecture, renowned for its strong performance and potential, is driving advances in AIOps. However, prior reviews leave gaps in explaining why Transformers trigger a major shift in academia and industry, with limited coverage of multimodal data (logs, metrics, events), insufficient analysis of structural and methodological connections between Transformers and AIOps, fragmented views of capabilities, and a lack of consolidated evaluation strategies. To bridge these gaps, our work decomposes “Why Transformers” into three questions. First, we review what roles Transformers assume in AIOps across 70 representative papers, using a structured taxonomy that proceeds sequentially from data to targets, principles, and approaches, which present an evolutionary trajectory of role changes. Then, to explain why Transformers excel, we introduce a capability framework comprising two basic and four advanced capabilities. As for how to evaluate Transformers in AIOps, we consolidate evaluation resources and strategies, including offline datasets, standardized questions, and real-time simulations. Furthermore, probable best practices are distilled, offering actionable guidance for real-world adoption. These explorations aim to clarify the internal rationale and unlock the practical value of Transformers in AIOps.
- Open Access
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 461-472
Bridging the Delay: Lag-Aware Spatio-Temporal Causal Inference for Microservice Root Cause Analysis
Timely root cause analysis (RCA) is essential for stable microservice operations, especially when failures propagate across services. In practice, upstream failures rarely trigger downstream alerts immediately; symptoms at dependent services often emerge seconds or minutes later. However, most existing RCA methods still analyze service interactions synchronously and fail to explicitly account for such multi-lag propagation, which misaligns causes and symptoms and can dilute true upstream culprits while over-ranking downstream victims. In this paper, we present LagRCA, a lag-aware spatio-temporal causal inference framework for microservice RCA. It models failure propagation with heterogeneous time lags, aligning upstream causes with lagged downstream symptoms. At the same time, it disentangles whether one service causally affects another from how strongly their service-level metrics co-fluctuate, preventing shared state changes from being misread as direct causal dependencies. It also produces interpretable propagation paths that help operators understand failure dynamics and act on diagnoses. We evaluate LagRCA on public microservice benchmarks and large-scale real incident data from Alibaba. Experimental results show that LagRCA consistently outperforms state-of-the-art RCA methods, achieving 88.3% top-five localization accuracy (outperforming the best baseline by 21.8 percentage points). Moreover, LagRCA has been deployed in Alibaba's production microservice environment, where it improves incident diagnosis efficiency and reduces manual troubleshooting effort.
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 461-472
Open AccessBridging the Delay: Lag-Aware Spatio-Temporal Causal Inference for Microservice Root Cause Analysis
Timely root cause analysis (RCA) is essential for stable microservice operations, especially when failures propagate across services. In practice, upstream failures rarely trigger downstream alerts immediately; symptoms at dependent services often emerge seconds or minutes later. However, most existing RCA methods still analyze service interactions synchronously and fail to explicitly account for such multi-lag propagation, which misaligns causes and symptoms and can dilute true upstream culprits while over-ranking downstream victims. In this paper, we present LagRCA, a lag-aware spatio-temporal causal inference framework for microservice RCA. It models failure propagation with heterogeneous time lags, aligning upstream causes with lagged downstream symptoms. At the same time, it disentangles whether one service causally affects another from how strongly their service-level metrics co-fluctuate, preventing shared state changes from being misread as direct causal dependencies. It also produces interpretable propagation paths that help operators understand failure dynamics and act on diagnoses. We evaluate LagRCA on public microservice benchmarks and large-scale real incident data from Alibaba. Experimental results show that LagRCA consistently outperforms state-of-the-art RCA methods, achieving 88.3% top-five localization accuracy (outperforming the best baseline by 21.8 percentage points). Moreover, LagRCA has been deployed in Alibaba's production microservice environment, where it improves incident diagnosis efficiency and reduces manual troubleshooting effort.
- Top Cited PapersOpen Access
- 11 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (1) , 1-55
Failure Diagnosis in Microservice Systems: A Comprehensive Survey and Analysis
Widely adopted for their scalability and flexibility, modern microservice systems present unique failure diagnosis challenges due to their independent deployment and dynamic interactions. This complexity can lead to cascading failures that negatively impact operational efficiency and user experience. Recognizing the critical role of fault diagnosis in improving the stability and reliability of microservice systems, researchers have conducted extensive studies and achieved a number of significant results. This survey provides an exhaustive review of 98 scientific papers from 2003 to the present, including a thorough examination and elucidation of the fundamental concepts, system architecture, and problem statement. It also includes a qualitative analysis of the dimensions, providing an in-depth discussion of current best practices and future directions, aiming to further its development and application. In addition, this survey compiles publicly available datasets, toolkits, and evaluation metrics to facilitate the selection and validation of techniques for practitioners.
- 11 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (1) , 1-55
Top Cited PapersOpen AccessFailure Diagnosis in Microservice Systems: A Comprehensive Survey and Analysis
Widely adopted for their scalability and flexibility, modern microservice systems present unique failure diagnosis challenges due to their independent deployment and dynamic interactions. This complexity can lead to cascading failures that negatively impact operational efficiency and user experience. Recognizing the critical role of fault diagnosis in improving the stability and reliability of microservice systems, researchers have conducted extensive studies and achieved a number of significant results. This survey provides an exhaustive review of 98 scientific papers from 2003 to the present, including a thorough examination and elucidation of the fundamental concepts, system architecture, and problem statement. It also includes a qualitative analysis of the dimensions, providing an in-depth discussion of current best practices and future directions, aiming to further its development and application. In addition, this survey compiles publicly available datasets, toolkits, and evaluation metrics to facilitate the selection and validation of techniques for practitioners.
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1180-1194
Effective Node-Level Anomaly Detection in HPC Systems via Coarse-Grained Clustering and Fine-Grained Model Sharing
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1180-1194
Open AccessEffective Node-Level Anomaly Detection in HPC Systems via Coarse-Grained Clustering and Fine-Grained Model Sharing
- Open Access
- 6 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 270-272
Efficient and Accurate Anomaly Detection in HPC Systems via Coarse-Grained Clustering and Fine-Grained Model Sharing
- 6 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 270-272
Open AccessEfficient and Accurate Anomaly Detection in HPC Systems via Coarse-Grained Clustering and Fine-Grained Model Sharing
- Open Access
- 6 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 241-243
Forewarned is Forearmed: Joint Prediction and Classification of Optical Transceiver Failures in Large-Scale LLM Training Clusters
- 6 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 241-243
Open AccessForewarned is Forearmed: Joint Prediction and Classification of Optical Transceiver Failures in Large-Scale LLM Training Clusters
- 31 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (6) , 4013-4026
No More Data Silos: Unified Microservice Failure Diagnosis With Temporal Knowledge Graph
Microservices improve the scalability and flexibility of monolithic architectures to accommodate the evolution of software systems, but the complexity and dynamics of microservices challenge system reliability. Ensuring microservice quality requires efficient failure diagnosis, including detection and triage. Failure detection involves identifying anomalous behavior within the system, while triage entails classifying the failure type and directing it to the engineering team for resolution. Unfortunately, current approaches reliant on single-modal monitoring data, such as metrics, logs, or traces, cannot capture all failures and neglect interconnections among multimodal data, leading to erroneous diagnoses. Recent multimodal data fusion studies struggle to achieve deep integration, limiting diagnostic accuracy due to insufficiently captured interdependencies. Therefore, we propose UniDiag , which leverages temporal knowledge graphs to fuse multimodal data for effective failure diagnosis. UniDiag applies a simple yet effective stream-based anomaly detection method to reduce computational cost and a novel microservice-oriented graph embedding method to represent the state of systems comprehensively. To assess the performance of UniDiag , we conduct extensive evaluation experiments using datasets from two benchmark microservice systems, demonstrating its superiority over existing methods and affirming the efficacy of multimodal data fusion. Additionally, we have publicly made the code and data available to facilitate further research.
- 31 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (6) , 4013-4026
No More Data Silos: Unified Microservice Failure Diagnosis With Temporal Knowledge Graph
Microservices improve the scalability and flexibility of monolithic architectures to accommodate the evolution of software systems, but the complexity and dynamics of microservices challenge system reliability. Ensuring microservice quality requires efficient failure diagnosis, including detection and triage. Failure detection involves identifying anomalous behavior within the system, while triage entails classifying the failure type and directing it to the engineering team for resolution. Unfortunately, current approaches reliant on single-modal monitoring data, such as metrics, logs, or traces, cannot capture all failures and neglect interconnections among multimodal data, leading to erroneous diagnoses. Recent multimodal data fusion studies struggle to achieve deep integration, limiting diagnostic accuracy due to insufficiently captured interdependencies. Therefore, we propose UniDiag , which leverages temporal knowledge graphs to fuse multimodal data for effective failure diagnosis. UniDiag applies a simple yet effective stream-based anomaly detection method to reduce computational cost and a novel microservice-oriented graph embedding method to represent the state of systems comprehensively. To assess the performance of UniDiag , we conduct extensive evaluation experiments using datasets from two benchmark microservice systems, demonstrating its superiority over existing methods and affirming the efficacy of multimodal data fusion. Additionally, we have publicly made the code and data available to facilitate further research.
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1183-1194
ART: A Unified Unsupervised Framework for Incident Management in Microservice Systems
Automated incident management is critical for large-scale microservice systems, including tasks such as anomaly detection (AD), failure triage (FT), and root cause localization (RCL). Currently, most techniques focus only on a single task, overlooking shared knowledge across closely related tasks. However, employing isolated models for managing multiple tasks may result in inefficiencies, delayed responses, a lack of systemic perspective, and complexity in updates and operations. Therefore we propose ART, an unsupervised framework that integrates a full-process solution covering Anomaly detection, failure Triage, and Root cause localization. It reaches the unification of multiple tasks by extracting the shared knowledge. Specifically, we first conduct an empirical study to analyze how the shared knowledge embedded in anomalous deviations manifests in AD, FT, and RCL. To better calculate deviations and extract shared knowledge, we sequentially model channel, temporal, and call dependencies using Transformer Encoder, GRU, and GraphSAGE, respectively. Then unified failure representations enhance the interpretability of abstract features with explicit semantic information, serving as the basis for unsupervised multitask solutions. Our evaluations on the datasets generated from two benchmark microservice systems demonstrate that ART outperforms existing methods in terms of AD (improving by 5.65% to 60.8%), FT (improving by 13.2% to 95.7%), and RCL (improving by 13.3% to 205%).
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1183-1194
Open AccessART: A Unified Unsupervised Framework for Incident Management in Microservice Systems
Automated incident management is critical for large-scale microservice systems, including tasks such as anomaly detection (AD), failure triage (FT), and root cause localization (RCL). Currently, most techniques focus only on a single task, overlooking shared knowledge across closely related tasks. However, employing isolated models for managing multiple tasks may result in inefficiencies, delayed responses, a lack of systemic perspective, and complexity in updates and operations. Therefore we propose ART, an unsupervised framework that integrates a full-process solution covering Anomaly detection, failure Triage, and Root cause localization. It reaches the unification of multiple tasks by extracting the shared knowledge. Specifically, we first conduct an empirical study to analyze how the shared knowledge embedded in anomalous deviations manifests in AD, FT, and RCL. To better calculate deviations and extract shared knowledge, we sequentially model channel, temporal, and call dependencies using Transformer Encoder, GRU, and GraphSAGE, respectively. Then unified failure representations enhance the interpretability of abstract features with explicit semantic information, serving as the basis for unsupervised multitask solutions. Our evaluations on the datasets generated from two benchmark microservice systems demonstrate that ART outperforms existing methods in terms of AD (improving by 5.65% to 60.8%), FT (improving by 13.2% to 95.7%), and RCL (improving by 13.3% to 205%).
- Top Cited Papers
- 27 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 16 (6) , 3851-3864
Robust Failure Diagnosis of Microservice System Through Multimodal Data
Automatic failure diagnosis is crucial for large microservice systems. Currently, most failure diagnosis methods rely solely on single-modal data (ie using either metrics, logs, or traces). In this study, we conduct an empirical study using real-world failure cases to show that combining these sources of data (multimodal data) leads to a more accurate diagnosis. However, effectively representing these data and addressing imbalanced failures remain challenging. To tackle these issues, we propose DiagFusion , a robust failure diagnosis approach that uses multimodal data. It leverages embedding techniques and data augmentation to represent the multimodal data of service instances, combines deployment data and traces to build a dependency graph, and uses a graph neural network to localize the root cause instance and determine the failure type. Our evaluations using real-world datasets show that DiagFusion, outperforms existing methods in terms of root cause instance localization (improving by 20.9% to 368%) and failure type determination (improving by 11.0% to 169%).
- 27 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 16 (6) , 3851-3864
Top Cited PapersRobust Failure Diagnosis of Microservice System Through Multimodal Data
Automatic failure diagnosis is crucial for large microservice systems. Currently, most failure diagnosis methods rely solely on single-modal data (ie using either metrics, logs, or traces). In this study, we conduct an empirical study using real-world failure cases to show that combining these sources of data (multimodal data) leads to a more accurate diagnosis. However, effectively representing these data and addressing imbalanced failures remain challenging. To tackle these issues, we propose DiagFusion , a robust failure diagnosis approach that uses multimodal data. It leverages embedding techniques and data augmentation to represent the multimodal data of service instances, combines deployment data and traces to build a dependency graph, and uses a graph neural network to localize the root cause instance and determine the failure type. Our evaluations using real-world datasets show that DiagFusion, outperforms existing methods in terms of root cause instance localization (improving by 20.9% to 368%) and failure type determination (improving by 11.0% to 169%).