提出ALERT方法，实时检测无线网络特征漂移并触发模型重训练。
A Representation Learning Approach to Feature Drift Detection in Wireless Networks
- 用MLP学习特征表示，结合统计检验与效用评估
- 在指纹识别和链路异常检测中优于10种主流方法
- 适合需要持续维护AI性能的无线网络场景
人工智能被视为下一代无线网络的核心，可实现普遍通信及新服务。然而在实际部署中，特征分布变化会降低AI模型性能，引发不良行为。为应对未被发现的模型退化，我们提出ALERT：一种能检测特征分布变化并触发模型重训练的方法，在无线指纹识别和链路异常检测两个用例中表现优异。ALERT包含三个组件：表示学习、统计检验和效用评估。表示学习采用MLP，统计检验使用柯尔莫哥洛夫-斯米尔诺夫检验与人群稳定性指数（Population Stability Index），并设计了新的效用评估函数。实验表明，该方法在两个无线网络场景中优于文献中十种标准漂移检测方法。
原文摘要 · Abstract (English)
AI is foreseen to be a centerpiece in next generation wireless networks enabling enabling ubiquitous communication as well as new services. However, in real deployment, feature distribution changes may degrade the performance of AI models and lead to undesired behaviors. To counter for undetected model degradation, we propose ALERT; a method that can detect feature distribution changes and trigger model re-training that works well on two wireless network use cases: wireless fingerprinting and link anomaly detection. ALERT includes three components: representation learning, statistical testing and utility assessment. We rely on MLP for designing the representation learning component, on Kolmogorov-Smirnov and Population Stability Index tests for designing the statistical testing and a new function for utility assessment. We show the superiority of the proposed method against ten standard drift detection methods available in the literature on two wireless network use cases.
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。