MODEL: Motif-based Deep Feature Learning for Link Prediction
This work addresses the problem of improving link prediction accuracy for network analysis applications, representing a novel method for a known bottleneck.
The paper tackles link prediction in networks by proposing a novel embedding algorithm that incorporates network motifs to capture higher-order structures, resulting in outperforming traditional similarity-based algorithms by 20% and state-of-the-art embedding-based algorithms by 19% across social, biological, and academic networks.
Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this paper, we propose a novel embedding algorithm that incorporates network motifs to capture higher-order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms by 20% and the state-of-the-art embedding-based algorithms by 19%.