Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
This addresses the problem of reliable OOD detection for machine learning practitioners, offering a practical solution for pre-trained models, though it appears incremental as it builds on existing smoothness concepts.
The paper tackles out-of-distribution (OOD) detection in Transformers by proposing a method based on between-layer transformation smoothness, which outperforms comparable methods without needing training data access.
Effective out-of-distribution (OOD) detection is crucial for reliable machine learning models, yet most current methods are limited in practical use due to requirements like access to training data or intervention in training. We present a novel method for detecting OOD data in Transformers based on transformation smoothness between intermediate layers of a network (BLOOD), which is applicable to pre-trained models without access to training data. BLOOD utilizes the tendency of between-layer representation transformations of in-distribution (ID) data to be smoother than the corresponding transformations of OOD data, a property that we also demonstrate empirically. We evaluate BLOOD on several text classification tasks with Transformer networks and demonstrate that it outperforms methods with comparable resource requirements. Our analysis also suggests that when learning simpler tasks, OOD data transformations maintain their original sharpness, whereas sharpness increases with more complex tasks.