Graph Convolution: A High-Order and Adaptive Approach
This addresses graph-structured data problems for applications like material design and drug screening, with incremental improvements in specific domains.
The paper tackles graph modeling by introducing a novel convolutional neural network framework with high-order convolution and adaptive filtering modules, achieving state-of-the-art performance on node classification and molecule property prediction tasks and generating 32% more real molecules for molecule generation.
In this paper, we presented a novel convolutional neural network framework for graph modeling, with the introduction of two new modules specially designed for graph-structured data: the $k$-th order convolution operator and the adaptive filtering module. Importantly, our framework of High-order and Adaptive Graph Convolutional Network (HA-GCN) is a general-purposed architecture that fits various applications on both node and graph centrics, as well as graph generative models. We conducted extensive experiments on demonstrating the advantages of our framework. Particularly, our HA-GCN outperforms the state-of-the-art models on node classification and molecule property prediction tasks. It also generates 32% more real molecules on the molecule generation task, both of which will significantly benefit real-world applications such as material design and drug screening.