Dimensionality Reduction Meets Message Passing for Graph Node Embeddings
This addresses a bottleneck in graph neural networks for applications like social network analysis and molecular modeling, but it is incremental as it builds on existing techniques.
The paper tackles the problem of GNNs struggling with long-range dependencies due to over-smoothing and over-squashing by proposing PCAPass, which combines PCA and message passing for unsupervised node embeddings, showing competitive performance on node classification benchmarks while gathering information from longer distances.
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.