Concise Logarithmic Loss Function for Robust Training of Anomaly Detection Model
This work addresses training stability issues for anomaly detection models, offering a potentially incremental improvement over existing loss functions.
The paper tackles the problem of training instability in deep learning-based anomaly detection models by proposing a novel logarithmic mean squared error (LMSE) loss function, which demonstrates superior loss convergence and anomaly detection performance compared to the widely used mean squared error (MSE).
Recently, deep learning-based algorithms are widely adopted due to the advantage of being able to establish anomaly detection models without or with minimal domain knowledge of the task. Instead, to train the artificial neural network more stable, it should be better to define the appropriate neural network structure or the loss function. For the training anomaly detection model, the mean squared error (MSE) function is adopted widely. On the other hand, the novel loss function, logarithmic mean squared error (LMSE), is proposed in this paper to train the neural network more stable. This study covers a variety of comparisons from mathematical comparisons, visualization in the differential domain for backpropagation, loss convergence in the training process, and anomaly detection performance. In an overall view, LMSE is superior to the existing MSE function in terms of strongness of loss convergence, anomaly detection performance. The LMSE function is expected to be applicable for training not only the anomaly detection model but also the general generative neural network.