MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
This work addresses a domain-specific problem in fields like drug and material design, offering incremental improvements over existing graph neural network approaches.
The paper tackled the problem of predicting interactions between structured entities, such as in drug design, by addressing limitations in existing graph neural networks that use fixed-size receptive fields and independent entity processing, resulting in improved prediction performance over state-of-the-art methods.
Predicting interactions between structured entities lies at the core of numerous tasks such as drug regimen and new material design. In recent years, graph neural networks have become attractive. They represent structured entities as graphs and then extract features from each individual graph using graph convolution operations. However, these methods have some limitations: i) their networks only extract features from a fix-sized subgraph structure (i.e., a fix-sized receptive field) of each node, and ignore features in substructures of different sizes, and ii) features are extracted by considering each entity independently, which may not effectively reflect the interaction between two entities. To resolve these problems, we present MR-GNN, an end-to-end graph neural network with the following features: i) it uses a multi-resolution based architecture to extract node features from different neighborhoods of each node, and, ii) it uses dual graph-state long short-term memory networks (L-STMs) to summarize local features of each graph and extracts the interaction features between pairwise graphs. Experiments conducted on real-world datasets show that MR-GNN improves the prediction of state-of-the-art methods.