Deep Learning or Classical Machine Learning? An Empirical Study on Log-Based Anomaly Detection
Boxi Yu, Jiayi Yao, Qiuai Fu, Zhiqing Zhong, Haotian Xie, Y.C. Wu, Yuchi Ma, Pinjia He
Abstract
While deep learning (DL) has emerged as a powerful technique, its benefits must be carefully considered in relation to computational costs. Specifically, although DL methods have achieved strong performance in log anomaly detection, they often require extended time for log preprocessing, model training, and model inference, hindering their adoption in online distributed cloud systems that require rapid deployment of log anomaly detection service.
Topics & Concepts
Anomaly detectionComputer scienceSoftware deploymentDeep learningInferenceArtificial intelligencePreprocessorMachine learningCloud computingAnomaly (physics)Relation (database)Online learningEmpirical researchData miningMathematicsSoftware engineeringPhysicsStatisticsCondensed matter physicsWorld Wide WebOperating systemSoftware System Performance and ReliabilityAnomaly Detection Techniques and ApplicationsNetwork Security and Intrusion Detection