网络结构学习的一种扩展激活图式
Spread-gram: A spreading-activation schema of network structural learning
摘要:
网络表示学习近年来呈爆炸式增长。然而,现有的研究通常将网络重构为序列或矩阵,这可能会导致模型训练过程中的信息偏差或稀疏性问题。受人类记忆认知模型的启发,我们提出了一个网络表示学习方案。在该方案中,我们通过调整遍历网络扩展结构的节点的接近度来学习节点嵌入。我们提出的方法显示了显着的改善,在多个分析任务的基础上,各种现实世界的网络,从语义网络,蛋白质相互作用网络,国际贸易网络,人类行为网络等,特别是,我们的模型可以有效地发现网络中的层次结构。组织良好的模型训练将收敛速度加快到只有少量的迭代,并且训练时间与边数呈线性关系。
英文摘要:
Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive model of human memory, we propose a network representation learning scheme. In this scheme, we learn node embeddings by adjusting the proximity of nodes traversing the spreading structure of the network. Our proposed method shows a significant improvement in multiple analysis tasks based on various real-world networks, ranging from semantic networks to protein interaction networks, international trade networks, human behavior networks, etc. In particular, our model can effectively discover the hierarchical structures in networks. The well-organized model training speeds up the convergence to only a small number of iterations, and the training time is linear with respect to the edge numbers.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。