From Data to Decision: A Multi-Stage Framework for Class Imbalance Mitigation in Optical Network Failure Analysis

2025-08-25

AI Summary

To address the severe class imbalance—where normal instances vastly outnumber fault instances—in optical network fault analysis, which degrades detection and identification performance, this paper proposes the first systematic three-stage imbalance-handling framework. It conducts the first direct comparative evaluation of preprocessing (e.g., random undersampling, SMOTE), in-model approaches (e.g., meta-learning), and postprocessing techniques (e.g., threshold tuning, generative AI). Experimental results demonstrate that postprocessing excels in fault detection: threshold tuning achieves up to a 15.3% F1-score improvement. For fault identification, generative AI delivers the highest accuracy gain—up to 24.2%—while maintaining both high precision and low inference latency under low-class-overlap conditions. Based on these findings, we propose an adaptive method selection strategy guided by data distribution characteristics and real-time constraints. This work establishes a practical, deployable imbalance learning paradigm for intelligent optical network operations and maintenance.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Algorithm Configuration
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Machine learning-based failure management in optical networks has gained significant attention in recent years. However, severe class imbalance, where normal instances vastly outnumber failure cases, remains a considerable challenge. While pre- and in-processing techniques have been widely studied, post-processing methods are largely unexplored. In this work, we present a direct comparison of pre-, in-, and post-processing approaches for class imbalance mitigation in failure detection and identification using an experimental dataset. For failure detection, post-processing methods-particularly Threshold Adjustment-achieve the highest F1 score improvement (up to 15.3%), while Random Under-Sampling provides the fastest inference. In failure identification, GenAI methods deliver the most substantial performance gains (up to 24.2%), whereas post-processing shows limited impact in multi-class settings. When class overlap is present and latency is critical, over-sampling methods such as the SMOTE are most effective; without latency constraints, Meta-Learning yields the best results. In low-overlap scenarios, Generative AI approaches provide the highest performance with minimal inference time.

Problem

• Addressing class imbalance in optical network failure analysis
• Comparing pre-, in-, and post-processing mitigation techniques
• Optimizing failure detection and identification performance metrics

Innovation

• Post-processing threshold adjustment for imbalance
• Generative AI methods for failure identification
• Meta-learning and SMOTE for different constraints