Topological Recurrent Neural Network for Diffusion Prediction
2017 IEEE International Conference on Data Mining (ICDM)(2017)
摘要
In this paper, we study the problem of using representation learning to assist information diffusion prediction on graphs. In particular, we aim at estimating the probability of an inactive node to be activated next in a cascade. Despite the success of recent deep learning methods for diffusion, we find that they often underexplore the cascade structure. We consider a cascade as not merely a sequence of nodes ordered by their activation time stamps; instead, it has a richer structure indicating the diffusion process over the data graph. As a result, we introduce a new data model, namely diffusion topologies, to fully describe the cascade structure. We find it challenging to model diffusion topologies, which are dynamic directed acyclic graphs (DAGs), with the existing neural networks. Therefore, we propose a novel topological recurrent neural network, namely Topo-LSTM, for modeling dynamic DAGs. We customize Topo-LSTM for the diffusion prediction task, and show it improves the state-of-the-art baselines, by 20.1%-56.6% (MAP) relatively, across multiple real-world data sets.
更多查看译文
关键词
topological recurrent neural network,representation learning,information diffusion prediction,inactive node,cascade structure,activation time stamps,diffusion process,data graph,data model,diffusion topologies,dynamic directed acyclic graphs,Topo-LSTM,diffusion prediction task,probability estimation,deep learning methods,neural networks,dynamic DAGs
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络