针对光网络故障分析中的类别不平衡问题，提出多阶段处理框架并验证各类方法效果。
From Data to Decision: A Multi-Stage Framework for Class Imbalance Mitigation in Optical Network Failure Analysis
- 对比预处理、内处理和后处理三类方法在故障检测与识别中的表现
- 后处理中阈值调整使故障检测F1提升15.3%，生成式AI在识别中性能增益达24.2%
- 根据重叠度与延迟需求推荐策略：低延迟选SMOTE，无约束用元学习，低重叠场景首选生成式AI
近年来，基于机器学习的光网络故障管理受到广泛关注。然而，正常实例远多于故障案例的严重类别不平衡仍是重大挑战。尽管预处理和内处理技术被广泛研究，后处理方法仍鲜有探索。本文使用实验数据集，直接比较了预处理、内处理和后处理在故障检测与识别中的表现。在故障检测中，后处理方法——尤其是阈值调整——实现最高F1分数提升（最高达15.3%），而随机欠采样提供最快推理速度。在故障识别中，生成式AI方法带来最大性能提升（最高达24.2%），后处理在多分类场景中影响有限。当存在类别重叠且延迟敏感时，过采样方法如SMOTE最有效；无延迟限制下，元学习表现最佳。在低重叠场景中，生成式AI在保持最小推理时间的同时达到最高性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。