Efficient Graph Optimization via Distance-Aware Graph Representation Learning
This addresses efficiency and robustness issues in graph neural networks for complex and noisy graph environments, representing an incremental improvement over existing methods.
The paper tackles the problem of inefficient graph representation learning by proposing a framework that integrates distance-aware multi-hop message passing with dynamic topology refinement, resulting in outperforming baseline GNNs in accuracy and scalability with at most 20% computational overhead.
We propose an efficient framework that integrates distance-aware multi-hop message passing with dynamic topology refinement. Unlike standard GNNs that rely on shallow, fixed-hop aggregation, DRTR leverages both static preprocessing and dynamic resampling to capture deeper structural dependencies. A \emph{Distance Recomputator} prunes semantically weak edges using adaptive attention, while a \emph{Topology Reconstructor} establishes latent connections among distant but relevant nodes. This joint mechanism enables more expressive and robust graph representation optimization across evolving graph structures. Extensive experiments demonstrate that DRTR outperforms baseline GNNs in both accuracy and scalability, with at most 20\% computational overhead, especially in complex and noisy graph environments.