Summary of Graph Neural Thompson Sampling, by Shuang Wu et al.
Graph Neural Thompson Sampling
by Shuang Wu, Arash A. Amini
First submitted to arxiv on: 15 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
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 paper proposes GNN-TS, an algorithm for online decision-making with a reward function defined over graph-structured data. It formulates the problem as an instance of graph action bandit and uses a Graph Neural Network (GNN) to estimate the mean reward function and uncertainty. The algorithm achieves a state-of-the-art regret bound that is sub-linear in the number of interaction rounds and independent of the number of graph nodes. Empirical results show that GNN-TS performs well on graph action bandit problems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about finding the best decision for online problems where the choices are connected in a special way, like a graph. It uses a new type of neural network called Graph Neural Network to make decisions and figure out how certain they are about those decisions. The algorithm gets better as it makes more decisions and doesn’t get worse just because there are more options. |
Keywords
* Artificial intelligence * Gnn * Graph neural network * Neural network
