Northwestern Polytechnical University, China.
Technical University of Darmstadt, Germany.
Neural Netw. 2021 Nov;143:345-354. doi: 10.1016/j.neunet.2021.06.018. Epub 2021 Jun 23.
Routing methods in capsule networks often learn a hierarchical relationship for capsules in successive layers, but the intra-relation between capsules in the same layer is less studied, while this intra-relation is a key factor for the semantic understanding in text data. Therefore, in this paper, we introduce a new capsule network with graph routing to learn both relationships, where capsules in each layer are treated as the nodes of a graph. We investigate strategies to yield adjacency and degree matrix with three different distances from a layer of capsules, and propose the graph routing mechanism between those capsules. We validate our approach on five text classification datasets, and our findings suggest that the approach combining bottom-up routing and top-down attention performs the best. Such an approach demonstrates generalization capability across datasets. Compared to the state-of-the-art routing methods, the improvements in accuracy in the five datasets we used were 0.82, 0.39, 0.07, 1.01, and 0.02, respectively.
胶囊网络中的路由方法通常在连续层的胶囊中学习层次关系，但同一层中胶囊之间的内部关系研究较少，而这种内部关系是文本数据中语义理解的关键因素。因此，在本文中，我们引入了一种具有图路由的新胶囊网络来学习这两种关系，其中每一层的胶囊都被视为图的节点。我们研究了从胶囊层的三种不同距离生成邻接和度矩阵的策略，并提出了这些胶囊之间的图路由机制。我们在五个文本分类数据集上验证了我们的方法，研究结果表明，结合自下而上路由和自上而下注意的方法表现最好。这种方法在不同数据集上具有很好的泛化能力。与最先进的路由方法相比，我们在使用的五个数据集上的准确性提高分别为 0.82、0.39、0.07、1.01 和 0.02。
