Anomaly Detection in Human Language via Meta-Learning: A Few-Shot Approach

TL;DR

This paper introduces a meta-learning framework that enables effective few-shot anomaly detection in human language across various domains, addressing challenges of data sparsity and variability.

Contribution

It presents a novel combination of episodic training, prototypical networks, and domain resampling for rapid adaptation to new language anomaly detection tasks.

Findings

Outperforms strong baselines in F1 and AUC scores

Effective generalization to unseen tasks with minimal labeled data

Releases code and benchmarks for further research

Abstract

We propose a meta learning framework for detecting anomalies in human language across diverse domains with limited labeled data. Anomalies in language ranging from spam and fake news to hate speech pose a major challenge due to their sparsity and variability. We treat anomaly detection as a few shot binary classification problem and leverage meta-learning to train models that generalize across tasks. Using datasets from domains such as SMS spam, COVID-19 fake news, and hate speech, we evaluate model generalization on unseen tasks with minimal labeled anomalies. Our method combines episodic training with prototypical networks and domain resampling to adapt quickly to new anomaly detection tasks. Empirical results show that our method outperforms strong baselines in F1 and AUC scores. We also release the code and benchmarks to facilitate further research in few-shot text anomaly detection.