New Influential Graph Neural Predictor (IGNP) framework enhances link prediction

Researchers have developed a new framework called the Influential Graph Neural Predictor (IGNP) for link prediction on multi-relational graphs. This method models the relationship between node pairs as influence propagation, extending the Susceptible-Infectious-Recovered (SIR) epidemic model to capture large-scale influence. The framework compresses sub-graphs using virtual edges to reduce computational load and has demonstrated superior performance over existing baselines on real-world datasets. AI

IMPACT This research could improve the accuracy of link prediction in complex networks, benefiting applications like social network analysis and knowledge graph completion.

RANK_REASON The cluster contains a research paper detailing a new method for link prediction on multi-relational graphs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Hugging Face
• Influential Graph Neural Predictor

• paper
• other

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