arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.00016cs.LGcs.AI
收藏

TransLog:一个基于Transformer的日志异常检测框架

TransLog: A Unified Transformer-based Framework for Log Anomaly Detection

State Key Lab of Software Development Environment, Beihang University(北京航空航天大学软件开发环境国家重点实验室);Cloudwise Research(云智慧研究院);University of Southern California(南加州大学);Bio-robot and human-computer interaction laboratory, Waseda University(早稻田大学生物机器人与人机交互实验室)

Hongcheng Guo, Xingyu Lin, Jian Yang, Yi Zhuang, Jiaqi Bai, Tieqiao Zheng, Bo Zhang, Zhoujun Li

摘要:

日志异常检测是IT运营人工智能(AIOps)领域的一个关键组成部分。考虑到不同域的日志数据,在实际工业场景中,特别是对于低资源域,对整个网络进行未知域的重新训练是低效的。然而,以往的深度模型只关注于提取同一领域的日志序列的语义,导致对多领域日志的泛化能力较差。因此,我们提出了一个统一的基于transformer的日志异常检测框架(\ourmethod{}),它包括预训练和基于适配器的调整阶段。我们的模型首先在源域上进行预训练,以获得日志数据的共享语义知识。然后,我们通过基于适配器的调整将预训练的模型转移到目标域。在三个公共数据集上对所提出的方法进行了评估,包括一个源域和两个目标域。实验结果表明,我们简单而有效的方法,在目标域中具有更少的可训练参数和更低的训练成本,在三个基准测试中达到了最先进的性能。

英文摘要:

Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps). Considering log data of variant domains, retraining the whole network for unknown domains is inefficient in real industrial scenarios especially for low-resource domains. However, previous deep models merely focused on extracting the semantics of log sequence in the same domain, leading to poor generalization on multi-domain logs. Therefore, we propose a unified Transformer-based framework for log anomaly detection (\ourmethod{}), which is comprised of the pretraining and adapter-based tuning stage. Our model is first pretrained on the source domain to obtain shared semantic knowledge of log data. Then, we transfer the pretrained model to the target domain via the adapter-based tuning. The proposed method is evaluated on three public datasets including one source domain and two target domains. The experimental results demonstrate that our simple yet efficient approach, with fewer trainable parameters and lower training costs in the target domain, achieves state-of-the-art performance on three benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑