Graph Neural Networks (GNNs) have received increasing attention for representation learning in various machine learning tasks. However, most existing GNNs applying neighborhood aggregation usually perform poorly on the graph with heterophily where adjacent nodes belong to different classes. In this paper, we show that in typical heterphilous graphs, the edges may be directed, and whether to treat the edges as is or simply make them undirected greatly affects the performance of the GNN models. Furthermore, due to the limitation of heterophily, it is highly beneficial for the nodes to aggregate messages from similar nodes beyond local neighborhood.These motivate us to develop a model that adaptively learns the directionality of the graph, and exploits the underlying long-distance correlations between nodes. We first generalize the graph Laplacian to digraph based on the proposed Feature-Aware PageRank algorithm, which simultaneously considers the graph directionality and long-distance feature similarity between nodes. Then digraph Laplacian defines a graph propagation matrix that leads to a model called {\em DiglacianGCN}. Based on this, we further leverage the node proximity measured by commute times between nodes, in order to preserve the nodes' long-distance correlation on the topology level. Extensive experiments on ten datasets with different levels of homophily demonstrate the effectiveness of our method over existing solutions in the task of node classification.
翻译:神经网图( GNNs) 在各种机器学习任务中,人们越来越关注代表性学习。 然而, 大部分应用周边聚合的GNNs在图形上表现不佳, 相邻节点属于不同类别。 在本文中, 我们显示, 在典型的超常图中, 边缘可能会被引导, 是否按原样处理边缘, 以及是否仅仅使它们不直接处理边缘, 也会大大影响 GNN 模型的性能。 此外, 由于节点之间的杂乱, 节点对集合来自当地附近类似节点的信息非常有益。 这会激励我们开发一个模型, 适应性地学习图的方向性, 并探索不同节点之间的长距离关系。 我们首先根据拟议中的“ 偏差- 软件” PageRank 算法, 将图形的边际线归纳为测量边际, 同时也考虑图形方向和长距离特征的相似性能。 然后, digraph Laplacecian 定义一个图形传播矩阵矩阵, 导致一个名为“ 数字- 数字- glacdededealGdealalal commalalal listal listal listal real ” 上, 我们进一步在不使用了“ robaltical deal lades ladeal ladeal ladeal lax lax lax lax lax lax lax lad 。