Loading...

Robust Semi-supervised Learning via f-Divergence and α-Rényi Divergence

Aminian, G ; Sharif University of Technology | 2024

150 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ISIT57864.2024.10619617
  3. Publisher: 2024
  4. Abstract:
  5. This paper investigates a range of empirical risk functions and regularization methods suitable for self-training methods in semi-supervised learning. These approaches draw inspiration from various divergence measures, such as f-di-vergences and α-Rényi divergences. Inspired by the theoretical foundations rooted in divergences, i.e., f-divergences and α-Rényi divergence, we also provide valuable insights to enhance the understanding of our empirical risk functions and regularization techniques. In the pseudo-labeling and entropy minimization techniques as self-training methods for effective semi-supervised learning, the self-training process has some inherent mismatch between the true label and pseudo-label (noisy pseudo-labels) and some of our empirical risk functions are robust, concerning noisy pseudo-labels. Under some conditions, our empirical risk functions demonstrate better performance when compared to traditional self-training methods. © 2024 IEEE
  6. Keywords:
  7. Adversarial machine learning ; Contrastive Learning ; Federated learning ; Risk assessment ; Divergence measures ; Empirical risks ; Function methods ; Regularization methods ; Risk function ; Self-training ; Semi-supervised learning ; Theoretical foundations ; Training methods ; Vergences ; Self-supervised learning
  8. Source: IEEE International Symposium on Information Theory - Proceedings ; 2024 , Pages 1842-1847 ; 21578095 (ISSN); 979-835038284-6 (ISBN)
  9. URL: https://www.tib.eu/en/search/id/ieee:5e02375457bea759b24f2f8b61c37dbb422457fb/Robust-Semi-supervised-Learning-via-f-Divergence?cHash=3e2e78c6cf4d148938fffd01f63e79dc