Nana Zhang’s scientific contributions

... On the other hand, and not necessarily related to the CDP (although it could be considered part of the objective), another very interesting context in which we believe the philosophy proposed in this paper could be exploited is in the analysis of node influence, in an effort to enhance the local information on which the heuristic models proposed in this regard are typically based [58][59][60]. ...

Reference:

Social Network Analysis: A Novel Paradigm for Improving Community Detection

... Non-negative matrix factorization (NMF) based methods [9,10] are widely accepted because not only do they consider community membership but also they are simple and effective. They show their efficiency in various types of community detection tasks like overlapping communities, communities in attributed networks and multiplex networks. ...

Reference:

Attributed Network Clustering through Mutual Affinity Propagated Non-negative Matrix Factorization

... Recently, NMF algorithms have been widely used in different types of networks to perform link prediction tasks, mainly due to the advantages of NMF such as dimensionality reduction, interpretability and network reconfiguration [28]. The core idea of most of the published NMF-based link prediction models is to map the adjacency matrix of the network to a low-dimensional latent space, then maintain the network structural information by graph regularization, and finally reconstruct the original network with minimum error [29][30][31]. Wang et al. [29] proposed a non-negative matrix factorization model based on the kernel framework, which preserves both local and global network structure information. Mahmoodi et al. [30] proposed the adversarial nonnegative matrix factorization link prediction model, which uses the common neighbor algorithm to maintain the local network structure. ...

Reference:

Pairwisely constrained symmetric non-negative matrix factorization for link prediction in complex networks using degree-related clustering coefficient and improved closeness centrality