CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Loss
This work addresses a domain-specific issue in ordinal classification for applications like medical imaging, where varying error margins are critical, but it is incremental as it builds on existing contrastive learning and margin-based methods.
The paper tackled the problem of ordinal classification where misclassification consequences vary between neighboring ranks, proposing CLOC with a multi-margin n-pair loss to learn ordered representations. The results show that CLOC outperforms existing methods on five real-world image datasets and one synthetic dataset, demonstrating improved interpretability and controllability.
In ordinal classification, misclassifying neighboring ranks is common, yet the consequences of these errors are not the same. For example, misclassifying benign tumor categories is less consequential, compared to an error at the pre-cancerous to cancerous threshold, which could profoundly influence treatment choices. Despite this, existing ordinal classification methods do not account for the varying importance of these margins, treating all neighboring classes as equally significant. To address this limitation, we propose CLOC, a new margin-based contrastive learning method for ordinal classification that learns an ordered representation based on the optimization of multiple margins with a novel multi-margin n-pair loss (MMNP). CLOC enables flexible decision boundaries across key adjacent categories, facilitating smooth transitions between classes and reducing the risk of overfitting to biases present in the training data. We provide empirical discussion regarding the properties of MMNP and show experimental results on five real-world image datasets (Adience, Historical Colour Image Dating, Knee Osteoarthritis, Indian Diabetic Retinopathy Image, and Breast Carcinoma Subtyping) and one synthetic dataset simulating clinical decision bias. Our results demonstrate that CLOC outperforms existing ordinal classification methods and show the interpretability and controllability of CLOC in learning meaningful, ordered representations that align with clinical and practical needs.