Link Prediction Model for Opportunistic Networks Based on Feature Fusion

Abstract

Link prediction is a hot issue in the research of network evolution. The existing methods employ a stacked structure, which feeds captured topology information into a time series model. However, the structure introduces network noise that affects the accurate extraction of temporal features and reduces the prediction accuracy. Motivated by feature fusion methods in the Computer Vision(CV), we introduce a link prediction model based on attentional feature fusion (AFF-LP), which automatically extracts network features through the Deep Learning. The proposed model leverages the self-attention mechanism to extract the topological and temporal features respectively. Moreover, the network features are fused based on a graph-level representation. With the help of a vector mapping model, the feature vectors are mapped to the future network topology. Three real opportunistic network datasets, ITC, MIT and Infocom06, are used for experiments. The experimental results show that the proposed model is more accurate and stable compared to other baseline methods.

A Semantic-Enhancement-Based Social Network User-Alignment Algorithm

“…However, mining the semantic features of users based on graph neural networks also captures feature noise and topological noise in social networks. AFF-LP [45] uses an attention mechanism to extract network topology and temporal features in order to reduce noise interference and improve the accuracy of the algorithm. Notably, this method only considers the effect of network noise, while failing to consider the feature noise due to user feature differences.…”