ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs

TL;DR

ComENet introduces a complete and efficient message passing scheme for 3D molecular graphs, achieving full 3D information incorporation with significantly improved speed and accuracy over prior methods.

Contribution

The paper proposes a novel message passing scheme within 1-hop neighborhoods that guarantees full 3D information completeness and enhances computational efficiency.

Findings

Achieves global and local 3D information completeness.

Orders of magnitude faster than previous methods.

Demonstrates superior performance on large real-world datasets.

Abstract

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 \underline{com}plete and \underline{e}fficient 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 (\url{https://github.com/divelab/DIG}).