Graph data augmentation plays a vital role in regularizing Graph Neural Networks (GNNs), which leverage information exchange along edges in graphs, in the form of message passing, for learning. Due to their effectiveness, simple edge and node manipulations (e.g., addition and deletion) have been widely used in graph augmentation. In this paper, we identify a limitation in such a common augmentation technique. That is, simple edge and node manipulations can create graphs with an identical structure or indistinguishable structures to message passing GNNs but of conflict labels, leading to the sample collision issue and thus the degradation of model performance. To address this problem, we propose SoftEdge, which assigns random weights to a portion of the edges of a given graph to construct dynamic neighborhoods over the graph. We prove that SoftEdge creates collision-free augmented graphs. We also show that this simple method obtains superior accuracy to popular node and edge manipulation approaches and notable resilience to the accuracy degradation with the GNN depth.
翻译:图形数据增强在将图形神经网络(GNNs)正规化方面发挥着至关重要的作用。 图形神经网络(GNNS)能够以传递信息的方式,在图表边缘进行信息交流, 以传递信息为形式, 学习。 由于它们的有效性, 简单的边缘和节点操作( 例如, 添加和删除) 被广泛用于图形增强 。 在本文中, 我们确定了这种常见的增强技术的局限性 。 即, 简单的边缘和节点操作可以创建具有相同结构或无法区分的结构的图形, 与传递GNS但带有冲突标签的信息相连接, 从而导致样本碰撞问题, 从而导致模型性能退化 。 为了解决这个问题, 我们建议 SoftEdge 将随机权重分配到特定图形边缘的一部分, 以构建图形上的动态区域 。 我们证明 SoftEdge 创建了无碰撞增强的图形 。 我们还表明, 这种简单方法在流行节点和边缘操纵方法上获得了更高的准确性, 并显著地适应了 GNNE 深度的精确性退化 。