Expectation-Complete Graph Representations with Homomorphisms

We investigate novel random graph embeddings that can be computed in expected polynomial time and are able to distinguish all non-isomorphic graphs in expectation. Previous graph embeddings have limited expressiveness and either cannot distinguish all graphs or cannot be computed efficiently for every graph. To be able to approximate arbitrary functions on graphs, we are interested in efficient alternatives that become arbitrary expressive with increasing resources. Our approach is based on Lovász’ characterisation of graph isomorphism through an infinite dimensional vector of homomorphism counts. Our empirical evaluation shows competitive results on several benchmark graph learning tasks.

  • Published in:
    Learning on Graphs
  • Type:
    Inproceedings
  • Authors:
    Welke, Pascal; Thiessen, Maximilian; Gärtner, Thomas
  • Year:
    2023

Citation information

Welke, Pascal; Thiessen, Maximilian; Gärtner, Thomas: Expectation-Complete Graph Representations with Homomorphisms, Learning on Graphs, 2023, https://openreview.net/forum?id=8GJyW4i2oST, Welke.etal.2023a,

Associated Lamarr Researchers

lamarr institute person Welke Pascal - Lamarr Institute for Machine Learning (ML) and Artificial Intelligence (AI)

Pascal Welke

Autor to the profile