Embedding temporal networks inductively via mining neighborhood and community influences

Meng Liu, Ziwei Quan, Jia-Ming Wu, Yong Liu, Meng Han

Abstract: Network embedding aims to generate an embedding for each node in a network, which facilitates downstream machine learning tasks such as node classification and link prediction. Current work mainly focuses on transductive network embedding, i.e. generating fixed node embeddings, which is not suitable for real-world applications. This paper proposes a novel continual temporal network embedding method called ConMNCI by mining neighborhood and community influences inductively. We propose an aggregator function that integrates neighborhood influence with community influence to generate node embeddings at any time, and introduce the idea from continual learning to enhance inductive learning. We conduct extensive experiments on several real-world datasets and compare ConMNCI with several state-of-the-art baseline methods on various tasks, including node classification and network visualization. The experimental results show that ConMNCI significantly outperforms the state-of-the-art baselines.