A Graph Laplacian Eigenvector-based Pre-training Method for Graph Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918191505080320 |
|---|---|
| author | Dai, Howard Njenga, Nyambura Madhu, Hiren Viswanath, Siddharth Pellico, Ryan Adelstein, Ian Krishnaswamy, Smita |
| author_facet | Dai, Howard Njenga, Nyambura Madhu, Hiren Viswanath, Siddharth Pellico, Ryan Adelstein, Ian Krishnaswamy, Smita |
| contents | The development of self-supervised graph pre-training methods is a crucial ingredient in recent efforts to design robust graph foundation models (GFMs). Structure-based pre-training methods are under-explored yet crucial for downstream applications which rely on underlying graph structure. In addition, pre-training traditional message passing GNNs to capture global and regional structure is often challenging due to the risk of oversmoothing as network depth increases. We address these gaps by proposing the Laplacian Eigenvector Learning Module (LELM), a novel pre-training module for graph neural networks (GNNs) based on predicting the low-frequency eigenvectors of the graph Laplacian. Moreover, LELM introduces a novel architecture that overcomes oversmoothing, allowing the GNN model to learn long-range interdependencies. Empirically, we show that models pre-trained via our framework outperform baseline models on downstream molecular property prediction tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Graph Laplacian Eigenvector-based Pre-training Method for Graph Neural Networks Dai, Howard Njenga, Nyambura Madhu, Hiren Viswanath, Siddharth Pellico, Ryan Adelstein, Ian Krishnaswamy, Smita Machine Learning The development of self-supervised graph pre-training methods is a crucial ingredient in recent efforts to design robust graph foundation models (GFMs). Structure-based pre-training methods are under-explored yet crucial for downstream applications which rely on underlying graph structure. In addition, pre-training traditional message passing GNNs to capture global and regional structure is often challenging due to the risk of oversmoothing as network depth increases. We address these gaps by proposing the Laplacian Eigenvector Learning Module (LELM), a novel pre-training module for graph neural networks (GNNs) based on predicting the low-frequency eigenvectors of the graph Laplacian. Moreover, LELM introduces a novel architecture that overcomes oversmoothing, allowing the GNN model to learn long-range interdependencies. Empirically, we show that models pre-trained via our framework outperform baseline models on downstream molecular property prediction tasks. |
| title | A Graph Laplacian Eigenvector-based Pre-training Method for Graph Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.02803 |