Graph Structure from Point Clouds: Geometric Attention is All You Need
This work addresses a domain-specific challenge in high energy physics by providing a learned solution to graph construction from point clouds, offering computational efficiency improvements.
The paper tackled the problem of constructing graph structures from point clouds, known as the Topology Problem, by proposing a geometric attention mechanism called GravNetNorm, which achieved competitive tagging accuracy on top jet tagging while using significantly fewer computational resources than comparable models.
The use of graph neural networks has produced significant advances in point cloud problems, such as those found in high energy physics. The question of how to produce a graph structure in these problems is usually treated as a matter of heuristics, employing fully connected graphs or K-nearest neighbors. In this work, we elevate this question to utmost importance as the Topology Problem. We propose an attention mechanism that allows a graph to be constructed in a learned space that handles geometrically the flow of relevance, providing one solution to the Topology Problem. We test this architecture, called GravNetNorm, on the task of top jet tagging, and show that it is competitive in tagging accuracy, and uses far fewer computational resources than all other comparable models.