A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks

Abstract

Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to improve model performance, which is often more accessible and ubiquitous. Self-supervised pre-training for transfer learning is becoming an increasingly popular technique to improve state-of-the-art results using unlabeled data. It involves first pre-training a model on a large amount of unlabeled data, then adapting the model to target tasks of interest. In this review, we survey self-supervised learning methods and their applications within the sequential transfer learning framework. We provide an overview of the taxonomy for self-supervised learning and transfer learning, and highlight some prominent methods for designing pre-training tasks across different domains. Finally, we discuss recent trends and suggest areas for future investigation.

References in corpus (9)

• Language Models are Few-Shot Learners
• An Overview of Multi-Task Learning in Deep Neural Networks
• ERNIE: Enhanced Representation through Knowledge Integration
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Jukebox: A Generative Model for Music
• A Mutual Information Maximization Perspective of Language Representation Learning
• Unsupervised Translation of Programming Languages
• LakhNES: Improving multi-instrumental music generation with cross-domain pre-training
• Deep Automated Multi-task Learning