Graph Neural Networks Offer Unsupervised Solution for Social Network Influence Maximization

Researchers have developed a new unsupervised graph neural network (GNN) framework to tackle the Minimum Dominating Set (MDS) problem, which is crucial for influence maximization in social networks. This novel approach eliminates the need for ground-truth solutions during training, making it more efficient. When trained on synthetic graphs, the GNN achieved significantly faster inference times compared to existing methods and demonstrated strong performance on real-world social network benchmarks, indicating its practical applicability for large-scale analysis. AI

IMPACT Provides a more efficient method for identifying influential nodes in social networks, potentially improving applications like viral marketing and public health interventions.

RANK_REASON Academic paper detailing a new method for a combinatorial optimization problem using graph neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• cs.LG
• DagsHub
• Gotit.pub
• graph neural networks
• Hugging Face
• IArxiv
• Influence Flower
• ScienceCast
• social networks

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →