作者: Zhen Chen , Hanghang Tong , Lei Ying
DOI: 10.1109/TKDE.2019.2905210
关键词:
摘要: Understanding diffusion processes in networks has emerged as an important research topic because of its wide range applications. Analysis traces can help us answer questions such the source(s) and role each node during process. However, large-scale networks, due to cost privacy concerns, it is almost impossible monitor entire network collect complete trace. In this paper, we tackle problem reconstructing history from a partial observation. We formulate reconstruction maximum posteriori (MAP) prove NP-hard. Then, propose step-by-step algorithm, which always produce that consistent with Our experimental results based on synthetic real show algorithm significantly outperforms some existing methods.