Summary of Influence Maximization Via Graph Neural Bandits, by Yuting Feng et al.
Influence Maximization via Graph Neural Bandits
by Yuting Feng, Vincent Y. F. Tan, Bogdan Cautis
First submitted to arxiv on: 18 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Social and Information Networks (cs.SI)
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 In this paper, researchers tackle a common challenge in Influence Maximization (IM), where the goal is to maximize the number of distinct users influenced by a set of initial influencers. They propose IM-GNB, a framework that combines neural bandit algorithms and graph convolutional networks (GCNs) to effectively balance exploration and exploitation. The approach estimates the probabilities of users being influenced by influencers, constructing both an exploitation graph and an exploration one. Through real-time seed node selection using GCNs, IM-GNB refines the influencers’ estimated rewards in each contextual setting. Experimental results on two large real-world datasets show that IM-GNB outperforms other baseline methods, significantly improving the spread outcome of diffusion campaigns when the underlying network is unknown. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this study, scientists look at how to best influence people’s opinions or behaviors. They want to find the right mix of trying new things and sticking with what works. To do this, they develop a special way of using neural networks and bandit algorithms. This method helps figure out which initial influencers are most likely to spread ideas farthest. The researchers test their approach on real-world data and show that it’s more effective than other methods in spreading influence when you don’t know the underlying network. |
Keywords
» Artificial intelligence » Diffusion
