We present ATLAS (Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs), a novel graph learning algorithm that addresses two important challenges in graph neural networks (GNNs). First, the accuracy of GNNs degrades when the graph is heterophilic. Second, iterative feature aggregation limits the scalability of GNNs to large graphs. We address these challenges by extracting topological information about graph communities at multiple levels of refinement, concatenating community assignments to the feature vector, and applying multilayer perceptrons (MLPs) to the resulting representation. This provides topological context about nodes and their neighborhoods without invoking aggregation. Because MLPs are typically more scalable than GNNs, our approach applies to large graphs without the need for sampling. Across a wide set of graphs, ATLAS achieves comparable accuracy to baseline methods, with gains as high as 20 percentage points over GCN for heterophilic graphs with negative structural bias and 11 percentage points over MLP for homophilic graphs. Furthermore, we show how multi-resolution community features systematically modulate performance in both homophilic and heterophilic settings, opening a principled path toward explainable graph learning.

翻译：本文提出ATLAS（面向同配与异配图的自适应拓扑大规模学习算法），这是一种新型图学习算法，旨在解决图神经网络（GNNs）面临的两大关键挑战。首先，当图呈现异配性时，GNN的预测精度会显著下降。其次，迭代式的特征聚合机制限制了GNN在大规模图上的可扩展性。为解决这些问题，我们通过提取多粒度层级的图社群拓扑信息，将社群分配结果与特征向量进行拼接，并对所得表征应用多层感知机（MLPs）。该方法能在不进行特征聚合的情况下，为节点及其邻域提供拓扑上下文信息。由于MLP通常比GNN更具可扩展性，我们的方法无需采样即可适用于大规模图处理。在多种图数据集上的实验表明，ATLAS取得了与基线方法相当的精度：对于存在负向结构偏置的异配图，其性能较图卷积网络（GCN）提升高达20个百分点；对于同配图，较MLP基线提升11个百分点。此外，我们揭示了多分辨率社群特征如何系统性地调节同配与异配场景下的模型性能，从而为可解释的图学习开辟了一条理论路径。