mlsanityData to 14 Oct 2026

Unsupervised Attributed Dynamic Network Embedding with Stability Guarantees

arXiv 2503.02859 ↗First posted 4 Mar 2025stat.ML cs.LG stat.MEcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 59 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

28 of 59 references.

References · 28

  1. 2017Inductive Representation Learning on Large Graphscited by 6,320
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  4. 2020Benchmarking Graph Neural Networkscited by 680
  5. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  6. 2020Inductive Representation Learning on Temporal Graphscited by 462
  7. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  8. 2018DynGEM: Deep Embedding Method for Dynamic Graphscited by 102
  9. 2018Streaming Graph Neural Networkscited by 91
  10. 2018dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learningcited by 88
  11. 2019Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluationscited by 50
  12. 2021Dynamic Network Embedding Surveycited by 44
16 more
  1. 2017Attributed Network Embedding for Learning in a Dynamic Environmentcited by 39
  2. 2020Latent Space Models for Dynamic Networkscited by 29
  3. 2020The multilayer random dot product graphcited by 19
  4. 2017A Review of Dynamic Network Models with Latent Variablescited by 18
  5. 2020ScreeNOT: Exact MSE-Optimal Singular Value Thresholding in Correlated Noisecited by 15
  6. 2021Spectral embedding for dynamic networks with stability guaranteescited by 13
  7. 2019Spectral embedding of weighted graphscited by 9
  8. 2020Spectral clustering on spherical coordinates under the degree-corrected stochastic blockmodelcited by 9
  9. 2023Unsupervised Embedding Quality Evaluationcited by 9
  10. 2020GloDyNE: Global Topology Preserving Dynamic Network Embeddingcited by 8
  11. 2023Collaborative Graph Neural Networks for Attributed Network Embeddingcited by 8
  12. 2023Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networkscited by 5
  13. 2023A Simple and Powerful Framework for Stable Dynamic Network Embeddingcited by 5
  14. 2016A General Framework for Content-enhanced Network Representation Learningcited by 2
  15. 2020Embedding Dynamic Attributed Networks by Modeling the Evolution Processescited by 2
  16. 2024Fast Truncated SVD of Sparse and Dense Matrices on Graphics Processorscited by 1

Built on by

Not cited yet.