Dynamic Graph Echo State Networks

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.

• Publication year

  2021

• Venue

  The European Symposium on Artificial Neural Networks

• Publication date

  2021-10-16

• Fields of study

  Computer Science

• Identifiers
  DOI 10.14428/esann/2021.ES2021-70arXiv 2110.08565
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Representation Learning for Dynamic Graphs: A Survey

  2019cited by this paper
• A Comprehensive Survey on Graph Neural Networks

  2019cited by this paper
• Temporal Graph Kernels for Classifying Dissemination Processes

  2019influential reference
• Fast and Deep Graph Neural Networks

  2019cited by this paper
• A Gentle Introduction to Deep Learning for Graphs

  2019cited by this paper
• Deep reservoir computing: A critical experimental analysis

  2017cited by this paper
• Echo State Property of Deep Reservoir Computing Networks

  2017cited by this paper
• Architectural and Markovian factors of echo state networks

  2011cited by this paper
• Graph Echo State Networks

  2010cited by this paper

• Refining High-Quality Labels Using Large Language Models to Enhance Node Classification in Graph Echo State Network

  2025cites this paper
• Adaptive Graph Echo State Network Based on Island Transpeciation Co-Evolution

  2025cites this paper
• How Minds Take Shape: Graph-ESN Reveals How Neural Ensembles Engineer Stable Representations

  2025cites this paper
• A Primer on Temporal Graph Learning

  2024cites this paper
• A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges

  2024cites this paper
• Leveraging the Power of Echo State Network for Enhanced Temporal Knowledge Graph Reasoning

  2024cites this paper
• Dynamical Graph Echo State Networks with Snapshot Merging for Dissemination Process Classification

  2023influential citation
• Filtration Surfaces for Dynamic Graph Classification

  2023cites this paper
• Fast and adaptive dynamics-on-graphs to dynamics-of-graphs translation

  2023cites this paper
• A Temporal Graphlet Kernel for Classifying Dissemination in Evolving Networks

  2022influential citation
• Using Connectome Features to Constrain Echo State Networks

  2022cites this paper
• Deep learning for graphs

  2021cites this paper