New SIMBA framework simplifies influence maximization with neural surrogates

Researchers have developed SIMBA, a new framework for influence maximization that moves away from complex neural networks and continuous optimization. SIMBA utilizes lightweight neural surrogates and direct discrete search, incorporating uniformly anchored node embeddings, a shallow graph neural network, and batched multi-swap simulated annealing. This approach significantly reduces computation time and improves influence spread and data efficiency compared to existing methods. AI

IMPACT Simplifies influence maximization techniques, potentially enabling broader application in network analysis and recommendation systems.

RANK_REASON The cluster contains a research paper detailing a new framework for influence maximization. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• ScienceCast

• paper
• other

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