Fast Propagation
Fast propagation research explores efficient methods for spreading information or influence across various structures, from graphs and networks to images and videos. Current efforts focus on improving the accuracy and efficiency of propagation algorithms, often employing techniques like message passing, transformer networks, and particle tracking, while addressing challenges such as computational cost and uncertainty quantification. These advancements have significant implications for diverse fields, including object detection in medical imaging, misinformation detection on social media, and improved efficiency in deep learning model training. The ultimate goal is to develop robust and scalable propagation methods for a wide range of applications.
Papers
Uncertainty Quantification and Propagation in Surrogate-based Bayesian Inference
Philipp Reiser, Javier Enrique Aguilar, Anneli Guthke, Paul-Christian Bürkner
StructComp: Substituting Propagation with Structural Compression in Training Graph Contrastive Learning
Shengzhong Zhang, Wenjie Yang, Xinyuan Cao, Hongwei Zhang, Zengfeng Huang