Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks
This addresses the problem of improving node classification in heterogeneous graphs for researchers and practitioners, though it appears incremental as it builds on existing GNN methods with a new optimization-based approach.
The paper tackles the challenge of balancing oversmoothing and capturing long-range dependencies in heterogeneous graph neural networks (GNNs) by proposing a novel architecture derived from optimization steps of a relation-aware energy function, achieving competitive node classification accuracy on 8 benchmarks.
Heterogeneous graph neural networks (GNNs) achieve strong performance on node classification tasks in a semi-supervised learning setting. However, as in the simpler homogeneous GNN case, message-passing-based heterogeneous GNNs may struggle to balance between resisting the oversmoothing that may occur in deep models, and capturing long-range dependencies of graph structured data. Moreover, the complexity of this trade-off is compounded in the heterogeneous graph case due to the disparate heterophily relationships between nodes of different types. To address these issues, we propose a novel heterogeneous GNN architecture in which layers are derived from optimization steps that descend a novel relation-aware energy function. The corresponding minimizer is fully differentiable with respect to the energy function parameters, such that bilevel optimization can be applied to effectively learn a functional form whose minimum provides optimal node representations for subsequent classification tasks. In particular, this methodology allows us to model diverse heterophily relationships between different node types while avoiding oversmoothing effects. Experimental results on 8 heterogeneous graph benchmarks demonstrates that our proposed method can achieve competitive node classification accuracy