OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System
This addresses challenges in dynamic machine learning environments for applications requiring adaptation to new data, though it appears incremental as it builds on existing post-training and contrastive methods.
The paper tackles open-world problems with label shift, covariate shift, and unknown classes, particularly when pre-training on imbalanced data, and shows that their method significantly outperforms state-of-the-art adaptation techniques in accuracy and efficiency.
The expansion of machine learning into dynamic environments presents challenges in handling open-world problems where label shift, covariate shift, and unknown classes emerge. Post-training methods have been explored to address these challenges, adapting models to newly emerging data. However, these methods struggle when the initial pre-training is performed on class-imbalanced datasets, limiting generalization to minority classes. To address this, we propose a method that effectively handles open-world problems even when pre-training is conducted on imbalanced data. Our contrastive-based pre-training approach enhances classification performance, particularly for underrepresented classes. Our post-training mechanism generates reliable pseudo-labels, improving model robustness against open-world problems. We also introduce selective activation criteria to optimize the post-training process, reducing unnecessary computation. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art adaptation techniques in both accuracy and efficiency across diverse open-world scenarios.