Summary of Xsemad: Explainable Semantic Anomaly Detection in Event Logs Using Sequence-to-sequence Models, by Kiran Busch et al.
xSemAD: Explainable Semantic Anomaly Detection in Event Logs Using Sequence-to-Sequence Models
by Kiran Busch, Timotheus Kampik, Henrik Leopold
First submitted to arxiv on: 28 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 The paper proposes xSemAD, a novel approach to identifying and explaining undesirable behavior in event logs. This is achieved by using a sequence-to-sequence model to provide extended explanations of semantically deviant behavior. Unlike traditional anomaly detection methods, which focus on statistically rare behavior, xSemAD learns constraints from process models and checks whether they hold in the given event log. The approach not only identifies anomalies but also provides insights into their nature, facilitating targeted corrective actions. Experimental results show that xSemAD outperforms existing state-of-the-art semantic anomaly detection methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps identify and explain bad behavior in process logs. It uses a special kind of AI model to go beyond just saying “this is weird” and actually tells us what’s going wrong. This can help make sense of complex data and guide fixes for problems that are happening in real-time. The approach is better than existing methods at finding these kinds of issues and understanding why they’re happening. |
Keywords
» Artificial intelligence » Anomaly detection » Sequence model
