Dynamic Graph Echo State Networks
Domenico Tortorella, Alessio Micheli

TL;DR
This paper introduces an extension of graph echo state networks tailored for dynamic temporal graphs, offering an efficient, train-free vector encoding method that performs comparably to existing kernel-based approaches in dissemination classification tasks.
Contribution
The paper presents a novel extension of graph echo state networks for dynamic graphs, including conditions for the echo state property and an analysis of reservoir layout effects.
Findings
Achieves accuracy comparable to temporal graph kernels
Provides an efficient, train-free encoding method
Demonstrates effectiveness on dissemination classification tasks
Abstract
Dynamic temporal graphs represent evolving relations between entities, e.g. interactions between social network users or infection spreading. We propose an extension of graph echo state networks for the efficient processing of dynamic temporal graphs, with a sufficient condition for their echo state property, and an experimental analysis of reservoir layout impact. Compared to temporal graph kernels that need to hold the entire history of vertex interactions, our model provides a vector encoding for the dynamic graph that is updated at each time-step without requiring training. Experiments show accuracy comparable to approximate temporal graph kernels on twelve dissemination process classification tasks.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Reservoir Computing · Advanced Memory and Neural Computing · Neural Networks and Applications
