论文标题
图形神经网络的高阶集合，张量分解
High-Order Pooling for Graph Neural Networks with Tensor Decomposition
论文作者
论文摘要
图形神经网络（GNN）由于其有效性和灵活性在建模各种图形结构数据时引起了人们的关注。退出GNN体系结构通常采用简单的汇总操作（例如总和，平均，最大）时，从本地社区汇总消息以更新节点表示或汇总节点表示从整个图表来计算图表表示。尽管简单有效，但这些线性操作并未对节点之间的高阶非线性相互作用进行建模。我们提出了张贴图神经网络（TGNN），这是一种依靠张量分解来建模高阶非线性节点相互作用的高度表达性GNN结构。 TGNN利用对称CP分解有效地参数化置换不变的多线性图来建模节点相互作用。对节点和图形分类任务的理论和经验分析表明，TGNN比竞争基准的优越性。特别是，TGNN在两个OGB节点分类数据集和一个OGB图分类数据集上实现了最稳定的结果。
Graph Neural Networks (GNNs) are attracting growing attention due to their effectiveness and flexibility in modeling a variety of graph-structured data. Exiting GNN architectures usually adopt simple pooling operations (eg. sum, average, max) when aggregating messages from a local neighborhood for updating node representation or pooling node representations from the entire graph to compute the graph representation. Though simple and effective, these linear operations do not model high-order non-linear interactions among nodes. We propose the Tensorized Graph Neural Network (tGNN), a highly expressive GNN architecture relying on tensor decomposition to model high-order non-linear node interactions. tGNN leverages the symmetric CP decomposition to efficiently parameterize permutation-invariant multilinear maps for modeling node interactions. Theoretical and empirical analysis on both node and graph classification tasks show the superiority of tGNN over competitive baselines. In particular, tGNN achieves the most solid results on two OGB node classification datasets and one OGB graph classification dataset.
