LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis

Lecheng Zheng, Zhengzhang Chen, Dongjie Wang, Chengyuan Deng, Reon Matsuoka, Haifeng Chen

Keywords: root cause analysis, multi-modal learning, microservice systems, benchmark data

Abstract: Root cause analysis (RCA) is crucial for enhancing the reliability and performance of complex systems. However, progress in this field has been hindered by the lack of large-scale, open-source datasets tailored for RCA. To bridge this gap, we introduce LEMMA-RCA, a large dataset designed for diverse RCA tasks across multiple domains and modalities. LEMMA-RCA features various real-world fault scenarios from Information Technology (IT) and Operational Technology (OT) systems, encompassing microservices, water distribution, and water treatment systems, with hundreds of system entities involved. We evaluate the performance of six baseline methods on LEMMA-RCA across various settings, including offline and online modes, as well as single and multi-modal configurations. Our study demonstrates the utility of LEMMA-RCA in facilitating fair evaluation and promoting the development of more robust RCA techniques. The dataset and code are publicly available at https://www.lemmarca.info.

Primary Area: datasets and benchmarks

Submission Number: 14059