文献类型：期刊文献

英文题名：CI-SNF: Exploiting contextual information to improve SNF based information retrieval

作者：Chen, Ning[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2019

卷号：52

起止页码：175

外文期刊名：INFORMATION FUSION

收录：;EI(收录号：20192006925027);WOS:【SCI-EXPANDED(收录号:WOS:000473800600015)】；

基金：This work was supported by the National Natural Science Foundation of China [grant number 61771196].

语种：英文

外文关键词：Information retrieval; Contextual re-ranking; Similarity fusion

摘要：Similarity networks contain important topological features and patterns critical to understanding interactions among samples in a large dataset. To create a comprehensive view of the interactions within a dataset, the Similarity Network Fusion (SNF) technique has been proposed to fuse the similarity networks based on different data types into one similarity network that represents the full spectrum of underlying data. In this paper, a modified version of SNF, which is named as Contextual Information based SNF (CI-SNF), is proposed. In CI-SNF, first, modified Jaccard distance is performed on the SNF fused similarity to utilize the contextual information contained in the fused similarity network. Second, the local consistency of samples from the same category is enhanced by speculating that the samples which are located high in the Jaccard distance based ranking list of a specific query are from the same category as the query. Third, the inverted index technique is introduced to utilize the sparsity property of the locally consistent similarity network to enhance the computational efficiency. To verify the effectiveness and efficiency of CI-SNF model, it is applied in four different tasks, Cover Song Identification (CSI), image classification, cancer subtype identification, and drug taxonomy, respectively. Extensive experiments on thirteen challenging datasets demonstrate that CI-SNF scheme outperforms state-of-the-art similarity fusion algorithms including SNF in all four tasks. It is also verified that utilizing the contextual information contained in the SNF-based similarity network helps to enhance the performance of the SNF-based scheme, further.