论文标题
全球结构信息在图形神经网络应用程序中的影响
The Impact of Global Structural Information in Graph Neural Networks Applications
论文作者
论文摘要
图神经网络（GNNS）依靠图结构来定义聚合策略，其中每个节点通过结合其邻居的信息来更新其表示形式。 GNNS的一个已知局限性是，随着层数的增加，信息变得平滑和压缩，并且节点嵌入变得难以区分，对性能产生了负面影响。因此，实用的GNN模型几乎没有层，并且仅利用每个节点周围有限的小社区来利用图形结构。不可避免地，实用的GNN不会根据图的全局结构捕获信息。尽管有几项研究研究GNN的局限性和表达性，但在图结构数据上实用应用是否需要全球结构知识的问题仍未得到解答。在这项工作中，我们通过向多种GNN模型访问全局信息并观察其对下游性能的影响，从经验上解决了这个问题。我们的结果表明，实际上，全球信息可以为常见的图形相关任务带来重大好处。我们进一步确定了一种新颖的正则化策略，该策略可导致所有被考虑的任务的平均准确性提高超过5％。
Graph Neural Networks (GNNs) rely on the graph structure to define an aggregation strategy where each node updates its representation by combining information from its neighbours. A known limitation of GNNs is that, as the number of layers increases, information gets smoothed and squashed and node embeddings become indistinguishable, negatively affecting performance. Therefore, practical GNN models employ few layers and only leverage the graph structure in terms of limited, small neighbourhoods around each node. Inevitably, practical GNNs do not capture information depending on the global structure of the graph. While there have been several works studying the limitations and expressivity of GNNs, the question of whether practical applications on graph structured data require global structural knowledge or not, remains unanswered. In this work, we empirically address this question by giving access to global information to several GNN models, and observing the impact it has on downstream performance. Our results show that global information can in fact provide significant benefits for common graph-related tasks. We further identify a novel regularization strategy that leads to an average accuracy improvement of more than 5% on all considered tasks.
