MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks
This work addresses a bottleneck in heterogeneous graph learning for researchers and practitioners, offering a more efficient and accurate method, though it appears incremental as it builds on existing metapath-based approaches.
The paper tackled the performance degradation and computational inefficiency in deep heterogeneous graph neural networks by introducing MECCH, a novel model that uses metapath contexts for lossless information aggregation, achieving superior prediction accuracy and improved computational efficiency on five real-world datasets for node classification and link prediction.
Heterogeneous graph neural networks (HGNNs) were proposed for representation learning on structural data with multiple types of nodes and edges. To deal with the performance degradation issue when HGNNs become deep, researchers combine metapaths into HGNNs to associate nodes closely related in semantics but far apart in the graph. However, existing metapath-based models suffer from either information loss or high computation costs. To address these problems, we present a novel Metapath Context Convolution-based Heterogeneous Graph Neural Network (MECCH). MECCH leverages metapath contexts, a new kind of graph structure that facilitates lossless node information aggregation while avoiding any redundancy. Specifically, MECCH applies three novel components after feature preprocessing to extract comprehensive information from the input graph efficiently: (1) metapath context construction, (2) metapath context encoder, and (3) convolutional metapath fusion. Experiments on five real-world heterogeneous graph datasets for node classification and link prediction show that MECCH achieves superior prediction accuracy compared with state-of-the-art baselines with improved computational efficiency.