DINE: A Framework for Deep Incomplete Network Embedding
This addresses a practical challenge for researchers and practitioners in network analysis who deal with incomplete data, but it is incremental as it builds on existing embedding techniques by adding completion and attribute integration.
The paper tackles the problem of learning node embeddings from incomplete networks, which are common in real-world applications, by proposing DINE, a method that completes missing nodes and edges using expectation-maximization and incorporates both network structures and node attributes. The results show superiority over state-of-the-art baselines in multi-label classification and link prediction tasks on three networks.
Network representation learning (NRL) plays a vital role in a variety of tasks such as node classification and link prediction. It aims to learn low-dimensional vector representations for nodes based on network structures or node attributes. While embedding techniques on complete networks have been intensively studied, in real-world applications, it is still a challenging task to collect complete networks. To bridge the gap, in this paper, we propose a Deep Incomplete Network Embedding method, namely DINE. Specifically, we first complete the missing part including both nodes and edges in a partially observable network by using the expectation-maximization framework. To improve the embedding performance, we consider both network structures and node attributes to learn node representations. Empirically, we evaluate DINE over three networks on multi-label classification and link prediction tasks. The results demonstrate the superiority of our proposed approach compared against state-of-the-art baselines.