TransLog: A Unified Transformer-based Framework for Log Anomaly Detection
This work addresses the need for efficient generalization in AIOps for low-resource domains, though it is incremental as it builds on existing Transformer and adapter methods.
The paper tackled the problem of inefficient retraining for log anomaly detection across multiple domains by proposing a unified Transformer-based framework with pretraining and adapter-based tuning, achieving state-of-the-art performance on three benchmarks with fewer trainable parameters and lower training costs.
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.