Search Results for author:
Found 3 papers, 3 papers with code
Tabular Data Contrastive Learning via Class-Conditioned and Feature-Correlation Based Augmentation
Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space.
Self-supervised Representation Learning From Random Data Projectors
Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations.
HiCu: Leveraging Hierarchy for Curriculum Learning in Automated ICD Coding
One of the challenges in curriculum learning is the design of curricula -- i. e., in the sequential design of tasks that gradually increase in difficulty.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
