SCNode: Spatial and Contextual Coordinates for Graph Representation Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912727093477376 |
|---|---|
| author | Uddin, Md Joshem Tola, Astrit Sikand, Varin Akcora, Cuneyt Gurcan Coskunuzer, Baris |
| author_facet | Uddin, Md Joshem Tola, Astrit Sikand, Varin Akcora, Cuneyt Gurcan Coskunuzer, Baris |
| contents | Effective node representation lies at the heart of Graph Neural Networks (GNNs), as it directly impacts their ability to perform downstream tasks such as node classification and link prediction. Most existing GNNs, particularly message passing graph neural networks, rely on neighborhood aggregation to iteratively compute node embeddings. While powerful, this paradigm suffers from well-known limitations of oversquashing, oversmoothing, and underreaching that degrade representation quality. More critically, MPGNNs often assume homophily, where connected nodes share similar features or labels, leading to poor generalization in heterophilic graphs where this assumption breaks down.
To address these challenges, we propose \textit{SCNode}, a \textit{Spatial-Contextual Node Embedding} framework designed to perform consistently well in both homophilic and heterophilic settings. SCNode integrates spatial and contextual information, yielding node embeddings that are not only more discriminative but also structurally aware. Our approach introduces new homophily matrices for understanding class interactions and tendencies. Extensive experiments on benchmark datasets show that SCNode achieves superior performance over conventional GNN models, demonstrating its robustness and adaptability in diverse graph structures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02158 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SCNode: Spatial and Contextual Coordinates for Graph Representation Learning Uddin, Md Joshem Tola, Astrit Sikand, Varin Akcora, Cuneyt Gurcan Coskunuzer, Baris Machine Learning Computational Geometry 68T07, 68R10 I.2.6; G.2.2 Effective node representation lies at the heart of Graph Neural Networks (GNNs), as it directly impacts their ability to perform downstream tasks such as node classification and link prediction. Most existing GNNs, particularly message passing graph neural networks, rely on neighborhood aggregation to iteratively compute node embeddings. While powerful, this paradigm suffers from well-known limitations of oversquashing, oversmoothing, and underreaching that degrade representation quality. More critically, MPGNNs often assume homophily, where connected nodes share similar features or labels, leading to poor generalization in heterophilic graphs where this assumption breaks down. To address these challenges, we propose \textit{SCNode}, a \textit{Spatial-Contextual Node Embedding} framework designed to perform consistently well in both homophilic and heterophilic settings. SCNode integrates spatial and contextual information, yielding node embeddings that are not only more discriminative but also structurally aware. Our approach introduces new homophily matrices for understanding class interactions and tendencies. Extensive experiments on benchmark datasets show that SCNode achieves superior performance over conventional GNN models, demonstrating its robustness and adaptability in diverse graph structures. |
| title | SCNode: Spatial and Contextual Coordinates for Graph Representation Learning |
| topic | Machine Learning Computational Geometry 68T07, 68R10 I.2.6; G.2.2 |
| url | https://arxiv.org/abs/2410.02158 |