论文标题
季节图神经网络
Quaternion Graph Neural Networks
论文作者
论文摘要
最近，图神经网络（GNN）已成为深度学习中的重要而积极的研究方向。值得注意的是，大多数现有的基于GNN的方法都学习欧几里得向量空间内的图表表示。除了欧几里得空间之外，超复杂空间中的学习表示和嵌入也已证明是一种有前途有效的方法。为此，我们提出了四元组图神经网络（QGNN）来学习四个空间内的图形表示。如前所述，与欧几里得和复杂的矢量空间相比，季节空间是一个超复杂矢量空间，通过汉密尔顿产品提供了高度有意义的计算和类似的微积分。我们的QGNN在用于图形分类和节点分类的一系列基准数据集上获得了最先进的结果。此外，关于知识图，我们基于QGNN的嵌入模型可以在三个新的且具有挑战性的基准数据集中获得最新的结果，以完成知识图的完成。我们的代码可在：\ url {https://github.com/daiquocnguyen/qgnn}中获得。
Recently, graph neural networks (GNNs) have become an important and active research direction in deep learning. It is worth noting that most of the existing GNN-based methods learn graph representations within the Euclidean vector space. Beyond the Euclidean space, learning representation and embeddings in hyper-complex space have also shown to be a promising and effective approach. To this end, we propose Quaternion Graph Neural Networks (QGNN) to learn graph representations within the Quaternion space. As demonstrated, the Quaternion space, a hyper-complex vector space, provides highly meaningful computations and analogical calculus through Hamilton product compared to the Euclidean and complex vector spaces. Our QGNN obtains state-of-the-art results on a range of benchmark datasets for graph classification and node classification. Besides, regarding knowledge graphs, our QGNN-based embedding model achieves state-of-the-art results on three new and challenging benchmark datasets for knowledge graph completion. Our code is available at: \url{https://github.com/daiquocnguyen/QGNN}.
