English

Dimensionality Reduction Meets Message Passing for Graph Node Embeddings

Machine Learning 2022-02-03 v2 Machine Learning

Abstract

Graph Neural Networks (GNNs) have become a popular approach for various applications, ranging from social network analysis to modeling chemical properties of molecules. While GNNs often show remarkable performance on public datasets, they can struggle to learn long-range dependencies in the data due to over-smoothing and over-squashing tendencies. To alleviate this challenge, we propose PCAPass, a method which combines Principal Component Analysis (PCA) and message passing for generating node embeddings in an unsupervised manner and leverages gradient boosted decision trees for classification tasks. We show empirically that this approach provides competitive performance compared to popular GNNs on node classification benchmarks, while gathering information from longer distance neighborhoods. Our research demonstrates that applying dimensionality reduction with message passing and skip connections is a promising mechanism for aggregating long-range dependencies in graph structured data.

Keywords

Cite

@article{arxiv.2202.00408,
  title  = {Dimensionality Reduction Meets Message Passing for Graph Node Embeddings},
  author = {Krzysztof Sadowski and Michał Szarmach and Eddie Mattia},
  journal= {arXiv preprint arXiv:2202.00408},
  year   = {2022}
}

Comments

Changed colors in figures 3 and 5 to match the others