# From Static to Dynamic Node Embeddings

arXiv: https://arxiv.org/abs/2009.10017 · HTML: https://mlsanity.com/paper/2009.10017/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 2 of 2)

- [From random-walks to graph-sprints: a low-latency node embedding framework on continuous-time dynamic graphs](https://mlsanity.com/paper/2307.08433/) (2023)
- [Deep-Graph-Sprints: Accelerated Representation Learning in Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2407.07712/) (2024)

## Abstract (arXiv)

We introduce a general framework for leveraging graph stream data for temporal prediction-based applications. Our proposed framework includes novel methods for learning an appropriate graph time-series representation, modeling and weighting the temporal dependencies, and generalizing existing embedding methods for such data. While previous work on dynamic modeling and embedding has focused on representing a stream of timestamped edges using a time-series of graphs based on a specific time-scale (e.g., 1 month), we propose the notion of an ε-graph time-series that uses a fixed number of edges for each graph, and show its superiority over the time-scale representation used in previous work. In addition, we propose a number of new temporal models based on the notion of temporal reachability graphs and weighted temporal summary graphs. These temporal models are then used to generalize existing base (static) embedding methods by enabling them to incorporate and appropriately model temporal dependencies in the data. From the 6 temporal network models investigated (for each of the 7 base embedding methods), we find that the top-3 temporal models are always those that leverage the new ε-graph time-series representation. Furthermore, the dynamic embedding methods from the framework almost always achieve better predictive performance than existing state-of-the-art dynamic node embedding methods that are developed specifically for such temporal prediction tasks. Finally, the findings of this work are useful for designing better dynamic embedding methods.