中科院数学与系统科学研究院

数学研究所

 

计算机科学研讨班

 

报告人    朱兴全 教授Florida Atlantic University

 Content and Structure Augmented Network Representation Learning

  2017.12.21(星期四),10:20-11:05

  点:数学院南楼N204

  要:Information network mining often requires examination of linkage relationships between nodes for analysis. Recently, network representation has emerged to represent each node in a vector format, embedding network structure, so off-the-shelf machine learning methods can be directly applied for analysis. To date, existing methods only focus on one aspect of node information and cannot leverage node labels. In this talk, we will propose a tri-party deep network representation model, using information from three parties: node structure, node content, and node labels (if available) to jointly learn optimal node representation. This model is based on a new coupled deep natural language module, whose learning is enforced at three levels: (1) at the network structure level, it exploits inter-node relationship by maximizing the probability of observing surrounding nodes given a node in random walks; (2) at the node content level, it captures node-word correlation by maximizing the co-occurrence of word sequence given a node; and (3) at the node label level, it models label-word correspondence by maximizing the probability of word sequence given a class label. The tri-party information is jointly fed into the neural network model to mutually enhance each other to learn optimal representation for effective learning.

附件
相关文档