论文标题
概括GNN中的聚合函数：通过非线性邻域聚合器的大容量GNN
Generalizing Aggregation Functions in GNNs:High-Capacity GNNs via Nonlinear Neighborhood Aggregators
论文作者
论文摘要
图形神经网络（GNN）在许多图形学习任务中取得了巨大的成功。为现有GNN提供动力的主要方面是多层网络体系结构，用于学习特定学习任务的非线性图表。 GNNS中的核心操作是消息传播，其中每个节点通过汇总其邻居的表示来更新其表示形式。现有的GNN主要在其消息传播中采用线性邻域聚集（均值，总和）或最大聚合器。 （1）对于线性聚合器，整个非线性和网络的GNN能力通常受到限制，因为更深的GNN通常会遇到过度平滑的问题。 （2）对于最大聚合器，通常无法意识到邻域内节点表示的详细信息。为了克服这些问题，我们重新考虑了GNN中的消息传播机制，并旨在开发GNN中邻里信息聚合的一般非线性聚合器。我们提出的非线性聚合器的一个主要方面是，它们在最大和均值/总计之间提供了最佳平衡的聚合器。因此，我们的聚合器可以继承（i）增加网络能力的高非线性和（ii）详细信息，从而在GNNS的消息传播中保留了表示形式的详细信息。在几个数据集上进行的有前途的实验显示了所提出的非线性聚合器的有效性。
Graph neural networks (GNNs) have achieved great success in many graph learning tasks. The main aspect powering existing GNNs is the multi-layer network architecture to learn the nonlinear graph representations for the specific learning tasks. The core operation in GNNs is message propagation in which each node updates its representation by aggregating its neighbors' representations. Existing GNNs mainly adopt either linear neighborhood aggregation (mean,sum) or max aggregator in their message propagation. (1) For linear aggregators, the whole nonlinearity and network's capacity of GNNs are generally limited due to deeper GNNs usually suffer from over-smoothing issue. (2) For max aggregator, it usually fails to be aware of the detailed information of node representations within neighborhood. To overcome these issues, we re-think the message propagation mechanism in GNNs and aim to develop the general nonlinear aggregators for neighborhood information aggregation in GNNs. One main aspect of our proposed nonlinear aggregators is that they provide the optimally balanced aggregators between max and mean/sum aggregations. Thus, our aggregators can inherit both (i) high nonlinearity that increases network's capacity and (ii) detail-sensitivity that preserves the detailed information of representations together in GNNs' message propagation. Promising experiments on several datasets show the effectiveness of the proposed nonlinear aggregators.
