One-Class Domain Adaptation via Meta-Learning

2025-01-22

AI Summary

Cross-domain anomaly detection in industrial IoT faces severe distribution shift and scarce anomalous samples in the target domain. Method: This paper introduces the novel task of One-Class Domain Adaptation (OC-DA), where adaptation relies solely on target-domain normal samples. We formally define the OC-DA problem, design a meta-task sampling strategy tailored for one-class adaptation, and propose OC-DA MAML—a meta-learning algorithm integrating one-class classification principles to model vibration sensor signals. Theoretical analysis provides convergence guarantees for the method. Results: Evaluated on the Rainbow-MNIST benchmark and real-world industrial vibration datasets, OC-DA MAML achieves an average 12.7% improvement in target-domain anomaly detection accuracy over standard MAML, demonstrating superior cross-domain generalization under extreme label scarcity.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The deployment of IoT (Internet of Things) sensor-based machine learning models in industrial systems for anomaly classification tasks poses significant challenges due to distribution shifts, as the training data acquired in controlled laboratory settings may significantly differ from real-time data in production environments. Furthermore, many real-world applications cannot provide a substantial number of labeled examples for each anomalous class in every new environment. It is therefore crucial to develop adaptable machine learning models that can be effectively transferred from one environment to another, enabling rapid adaptation using normal operational data. We extended this problem setting to an arbitrary classification task and formulated the one-class domain adaptation (OC-DA) problem setting. We took a meta-learning approach to tackle the challenge of OC-DA, and proposed a task sampling strategy to adapt any bi-level meta-learning algorithm to OC-DA. We modified the well-established model-agnostic meta-learning (MAML) algorithm and introduced the OC-DA MAML algorithm. We provided a theoretical analysis showing that OC-DA MAML optimizes for meta-parameters that enable rapid one-class adaptation across domains. The OC-DA MAML algorithm is evaluated on the Rainbow-MNIST meta-learning benchmark and on a real-world dataset of vibration-based sensor readings. The results show that OC-DA MAML significantly improves the performance on the target domains and outperforms MAML using the standard task sampling strategy.

Problem

• Machine Learning Adaptation
• Single Category Data
• Domain Adaptation

Innovation

• Meta-Learning
• Single-Class Domain Adaptation
• Sampling Strategy