Lifelong representation learning in dynamic attributed networks

Abstract Network embedding or network representation learning aims at learning a low-dimensional vector for each node in a network. The learned embeddings could advance various learning tasks in the network analysis area. Most existing embedding methods focus on plain and static networks while ignoring network dynamics. However, in real world networks, structure often evolves over time. In addition, many networks contain rich attributes and their attributes are changing over time. Naively applying existing embedding algorithms to each snapshot of dynamic network independently usually leads to unsatisfactory performance. In this paper, we present a Lifelong Dynamic Attributed Network Embedding Framework – LDANE. LDANE has a good mechanism to automatically expand the deep neural networks with the sizes of network growing and preserving what have learned from previous time steps. Furthermore, the proposed framework is carefully designed to flexibly incorporate the topology and attribute of nodes. We perform extensive experiments on both synthetic and real attributed networks to corroborate the significant advantages of the proposed framework compared with the existing state-of-the-art embedding techniques.