Unsupervised Attributed Dynamic Network Embedding with Stability Guarantees
This addresses the challenge of comparing nodes across time in dynamic networks with attributes, which is important for applications like social network analysis, though it appears to be an incremental advance in network embedding methods.
The authors tackled the problem of learning stable embeddings for dynamic attributed networks, where nodes have time-varying attributes, by proposing AUASE (attributed unfolded adjacency spectral embedding). They demonstrated that AUASE provides significant improvements for link prediction and node classification compared to state-of-the-art methods on four real attributed networks.
Stability for dynamic network embeddings ensures that nodes behaving the same at different times receive the same embedding, allowing comparison of nodes in the network across time. We present attributed unfolded adjacency spectral embedding (AUASE), a stable unsupervised representation learning framework for dynamic networks in which nodes are attributed with time-varying covariate information. To establish stability, we prove uniform convergence to an associated latent position model. We quantify the benefits of our dynamic embedding by comparing with state-of-the-art network representation learning methods on four real attributed networks. To the best of our knowledge, AUASE is the only attributed dynamic embedding that satisfies stability guarantees without the need for ground truth labels, which we demonstrate provides significant improvements for link prediction and node classification.