Summary of Reinforcement Learning-guided Semi-supervised Learning, by Marzi Heidari et al.
Reinforcement Learning-Guided Semi-Supervised Learning
by Marzi Heidari, Hanping Zhang, Yuhong Guo
First submitted to arxiv on: 2 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Reinforcement Learning Guided Semi-Supervised Learning (RLGSSL) method formulates SSL as a one-armed bandit problem, deploying an innovative RL loss based on weighted rewards to adaptively guide the learning process of the prediction model. RLGSSL incorporates a carefully designed reward function balancing labeled and unlabeled data for enhanced generalization performance. A semi-supervised teacher-student framework increases learning stability. Extensive experiments demonstrate superior performance compared to state-of-the-art SSL methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Semi-supervised learning (SSL) uses both labeled and unlabeled data to improve model performance, especially when labeled data is scarce. The current SSL methods rely on heuristics or predefined rules for generating pseudo-labels and leveraging unlabeled data. A new method called RLGSSL proposes using Reinforcement Learning (RL) to guide the learning process of the prediction model. This approach balances the use of labeled and unlabeled data to enhance generalization performance. The results show that this method performs better than other SSL methods. |
Keywords
» Artificial intelligence » Generalization » Reinforcement learning » Semi supervised
