# Unsupervised Attributed Dynamic Network Embedding with Stability Guarantees

arXiv: https://arxiv.org/abs/2503.02859 · HTML: https://mlsanity.com/paper/2503.02859/

## 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 (most cited first, 28 of 28)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [DynGEM: Deep Embedding Method for Dynamic Graphs](https://mlsanity.com/paper/1805.11273/) (2018)
- [Streaming Graph Neural Networks](https://mlsanity.com/paper/1810.10627/) (2018)
- [dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning](https://mlsanity.com/paper/1809.02657/) (2018)
- [Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations](https://mlsanity.com/paper/1906.05017/) (2019)
- [Dynamic Network Embedding Survey](https://mlsanity.com/paper/2103.15447/) (2021)
- [Attributed Network Embedding for Learning in a Dynamic Environment](https://mlsanity.com/paper/1706.01860/) (2017)
- [Latent Space Models for Dynamic Networks](https://mlsanity.com/paper/2005.08808/) (2020)
- [The multilayer random dot product graph](https://mlsanity.com/paper/2007.10455/) (2020)
- [A Review of Dynamic Network Models with Latent Variables](https://mlsanity.com/paper/1711.10421/) (2017)
- [ScreeNOT: Exact MSE-Optimal Singular Value Thresholding in Correlated Noise](https://mlsanity.com/paper/2009.12297/) (2020)
- [Spectral embedding for dynamic networks with stability guarantees](https://mlsanity.com/paper/2106.01282/) (2021)
- [Spectral embedding of weighted graphs](https://mlsanity.com/paper/1910.05534/) (2019)
- [Spectral clustering on spherical coordinates under the degree-corrected stochastic blockmodel](https://mlsanity.com/paper/2011.04558/) (2020)
- [Unsupervised Embedding Quality Evaluation](https://mlsanity.com/paper/2305.16562/) (2023)
- [GloDyNE: Global Topology Preserving Dynamic Network Embedding](https://mlsanity.com/paper/2008.01935/) (2020)
- [Collaborative Graph Neural Networks for Attributed Network Embedding](https://mlsanity.com/paper/2307.11981/) (2023)
- [Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks](https://mlsanity.com/paper/2306.06155/) (2023)
- [A Simple and Powerful Framework for Stable Dynamic Network Embedding](https://mlsanity.com/paper/2311.09251/) (2023)
- [A General Framework for Content-enhanced Network Representation Learning](https://mlsanity.com/paper/1610.02906/) (2016)
- [Embedding Dynamic Attributed Networks by Modeling the Evolution Processes](https://mlsanity.com/paper/2010.14047/) (2020)
- [Fast Truncated SVD of Sparse and Dense Matrices on Graphics Processors](https://mlsanity.com/paper/2403.06218/) (2024)

## 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.