From Zero to Hero: Cold-Start Anomaly Detection
Tal Reiss, George Kour, Naama Zwerdling, Ateret Anaby Tavor, Yedid Hoshen
Abstract
When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such “cold-start” cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics.- Anthology ID:
- 2024.findings-acl.453
- Volume:
- Findings of the Association for Computational Linguistics ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand and virtual meeting
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7607–7617
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.453
- DOI:
- Cite (ACL):
- Tal Reiss, George Kour, Naama Zwerdling, Ateret Anaby Tavor, and Yedid Hoshen. 2024. From Zero to Hero: Cold-Start Anomaly Detection. In Findings of the Association for Computational Linguistics ACL 2024, pages 7607–7617, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- From Zero to Hero: Cold-Start Anomaly Detection (Reiss et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2024.findings-acl.453.pdf