Customizing Graph Neural Networks using Path Reweighting
This addresses the need for more effective and robust GNNs for graph-structured data mining, though it appears incremental as it builds on existing GNN frameworks with a novel adaptation.
The paper tackles the problem of traditional Graph Neural Networks (GNNs) not distinguishing among downstream tasks by proposing CustomGNN, which uses path reweighting to learn task-specific semantics and achieves state-of-the-art accuracies on node classification across multiple datasets.
Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them are not always effective. Intuitively, paths in a graph imply different semantics for different downstream tasks. Inspired by this, we design a novel GNN solution, namely Customized Graph Neural Network with Path Reweighting (CustomGNN for short). Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph. Furthermore, we empirically analyze the semantics learned by CustomGNN and demonstrate its ability to avoid the three inherent problems in traditional GNNs, i.e., over-smoothing, poor robustness, and overfitting. In experiments with the node classification task, CustomGNN achieves state-of-the-art accuracies on three standard graph datasets and four large graph datasets. The source code of the proposed CustomGNN is available at \url{https://github.com/cjpcool/CustomGNN}.