Summary of Online Multi-modal Root Cause Analysis, by Lecheng Zheng et al.
Online Multi-modal Root Cause Analysis
by Lecheng Zheng, Zhengzhang Chen, Haifeng Chen, Jingrui He
First submitted to arxiv on: 13 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel online multi-modal causal structure learning method for root cause localization in microservice systems, called OCEAN, is introduced in this paper. Traditional RCA methods are limited by high computational demands or handle only single-modal data, overlooking complex interactions in multi-modal systems. OCEAN employs dilated convolutional neural networks and graph neural networks to capture temporal dependencies and causal relationships, and a multi-factor attention mechanism to analyze different metrics and log indicators/attributes. A contrastive mutual information maximization-based graph fusion module is also developed to model relationships across modalities. The proposed method is demonstrated to be effective and efficient through extensive experiments on three real-world datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, researchers develop a new way to find the root cause of problems in complex systems made up of many small services. Current methods are too slow or can only look at one type of data, so they don’t work well for these kinds of systems. The new method, called OCEAN, uses special types of neural networks to learn about the relationships between different parts of the system and how they change over time. It also has a way to focus on the most important information from different sources. The researchers tested their method with real-world data and found that it works well. |
Keywords
» Artificial intelligence » Attention » Multi modal
