Metapath Context Convolutions vs. Standard Message-Passing in Large-Scale Heterogeneous Graph Neural Networks

This report synthesises findings from 10 peer-reviewed papers addressing the following research question: What is the efficiency trade-off in terms of inference time and memory usage between standard message-passing HGNNs and HGNNs with metapath context convolution on large-scale graph-structured code. Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic superclass of traditional homogeneous networks (graphs). Meanwhile, representation learning (

Research goal: What is the efficiency trade-off in terms of inference time and memory usage between standard message-passing HGNNs and HGNNs with metapath context convolution on large-scale graph-structured code datasets?

Autonomous literature synthesis. Automated review score: 7.5/10. Full text and citation available at Assignee Research.