Graph Propagation Efficiency
Petar explains the importance of efficient data propagation in tasks like molecular property predictions. By utilizing expander graphs with low bottlenecks and high global information propagation, their method, expanded graph propagation, overcomes scalability challenges in graph-based machine learning models.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Related Questions