Learning from tabular data with out-of-distribution characteristics

• OOD data significantly impacts model performance, resulting in decreased prediction accuracy and reliability. • The continual tabular contrastive learning (C-TCL) method effectively manages OOD data while maintaining computational efficiency. • C-TCL achieves superior performance on CPU hardware, making it more accessible than GPU-based alternatives. • Experimental results from eight diverse datasets demonstrate C-TCL’s effectiveness, particularly in classification tasks. • The matrix augmentation technique using full data representation improves model efficiency compared to traditional slice-based methods. • Simplified contrastive loss calculations with dot product reduces computational overhead while maintaining performance.