2022/06/17 by Limei Wang, Yi Liu, Wang, Limei +7 · 15 citations
Computer Science · Engineering · Materials Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Hydrocarbon exploration and reservoir analysis #Machine Learning (cs.LG) #Machine Learning in Materials Science #cs.LG
paper · pdf · doi:10.48550/arxiv.2206.08515
The paper has been accepted by NeurIPS 2022. You can also cite the conference version
openalex publication_date 2022/06/17 · openalex created_date 2022/06/22 · arxiv created 2022/09/29 · arxiv updated 2022/09/30 · openalex updated_date 2026/07/28
Many real-world data can be modeled as 3D graphs, but learning representations that incorporates 3D information completely and efficiently is challenging. Existing methods either use partial 3D information, or suffer from excessive computational cost. To incorporate 3D information completely and efficiently, we propose a novel message passing scheme that operates within 1-hop neighborhood. Our method guarantees full completeness of 3D information on 3D graphs by achieving global and local completeness. Notably, we propose the important rotation angles to fulfill global completeness. Additionally, we show that our method is orders of magnitude faster than prior methods. We provide rigorous proof of completeness and analysis of time complexity for our methods. As molecules are in essence quantum systems, we build the \underlinecomplete and \underlineefficient graph neural network (ComENet) by combing quantum inspired basis functions and the proposed message passing scheme. Experimental results demonstrate the capability and efficiency of ComENet, especially on real-world datasets that are large in both numbers and sizes of graphs. Our code is publicly available as part of the DIG library (\urlhttps://github.com/divelab/DIG).