🤖 AI Summary
Existing GNN methods (e.g., GAMLP, ImprovingTE) rely on predefined sampling strategies for k-hop structural learning, resulting in poor generalizability and weak robustness. To address this, we propose DRTR (Distance Recomputator & Topology Reconstructor), an adaptive neighborhood reconstruction framework that— for the first time—jointly models distance recalibration and dynamic local topology reconstruction. DRTR employs graph-property-driven distance re-evaluation, coreset-inspired neighborhood selection, and multi-hop-structure-aware message passing to achieve context-aware and robust k-hop information aggregation. Evaluated on multiple benchmark datasets, DRTR consistently outperforms state-of-the-art models in both predictive accuracy and stability under noisy or mislabeled conditions.
📝 Abstract
Graph Neural Networks (GNNs) have become fundamental in semi-supervised learning for graph representation, leveraging their ability to capture complex node relationships. A recent trend in GNN research focuses on extbf{adaptive k-hop structure learning}, moving beyond fixed-hop aggregation to more flexible and dynamic neighborhood selection. While GAMLP cite{Zhang_2022} employs separate MLP layers for each k-hop domain and ImprovingTE cite{Yao2023ImprovingTE} enhances this by injecting contextualized substructure information, these methods still rely heavily on predefined sampling strategies, which may limit their ability to generalize and maintain stable accuracy. To address these limitations, we propose an extbf{adaptive reconstruction framework} that dynamically refines k-hop structure learning. Inspired by"coreset selection"cite{guo2022deepcore}, our approach adaptively extbf{reconstructs} node neighborhoods to optimize message passing, ensuring more extbf{effective and context-aware information flow} across the graph. To further enhance structural robustness, we introduce two key modules: the extbf{Distance Recomputator} and the extbf{Topology Reconstructor} ( extcolor{blue}{DRTR}). The Distance Recomputator extbf{reassesses and recalibrates} node distances based on adaptive graph properties, leading to extbf{improved node embeddings} that better reflect latent relationships. Meanwhile, the Topology Reconstructor extbf{dynamically refines local graph structures}, enabling the model to extbf{adapt to evolving graph topologies} and mitigate the impact of noise and mislabeled data. Empirical evaluations demonstrate that our extbf{adaptive reconstruction framework} achieves extbf{significant improvements} over existing k-hop-based models, providing more extbf{stable and accurate} performance in various graph learning benchmarks.