FUSE: Fast Semi-Supervised Node Embedding Learning via Structural and Label-Aware Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909841503551488 |
|---|---|
| author | Chakraborty, Sujan Bordoloi, Rahul Sengupta, Anindya Wolkenhauer, Olaf Bej, Saptarshi |
| author_facet | Chakraborty, Sujan Bordoloi, Rahul Sengupta, Anindya Wolkenhauer, Olaf Bej, Saptarshi |
| contents | Graph-based learning is a cornerstone for analyzing structured data, with node classification as a central task. However, in many real-world graphs, nodes lack informative feature vectors, leaving only neighborhood connectivity and class labels as available signals. In such cases, effective classification hinges on learning node embeddings that capture structural roles and topological context. We introduce a fast semi-supervised embedding framework that jointly optimizes three complementary objectives: (i) unsupervised structure preservation via scalable modularity approximation, (ii) supervised regularization to minimize intra-class variance among labeled nodes, and (iii) semi-supervised propagation that refines unlabeled nodes through random-walk-based label spreading with attention-weighted similarity. These components are unified into a single iterative optimization scheme, yielding high-quality node embeddings. On standard benchmarks, our method consistently achieves classification accuracy at par with or superior to state-of-the-art approaches, while requiring significantly less computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_11250 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FUSE: Fast Semi-Supervised Node Embedding Learning via Structural and Label-Aware Optimization Chakraborty, Sujan Bordoloi, Rahul Sengupta, Anindya Wolkenhauer, Olaf Bej, Saptarshi Machine Learning I.5.2 Graph-based learning is a cornerstone for analyzing structured data, with node classification as a central task. However, in many real-world graphs, nodes lack informative feature vectors, leaving only neighborhood connectivity and class labels as available signals. In such cases, effective classification hinges on learning node embeddings that capture structural roles and topological context. We introduce a fast semi-supervised embedding framework that jointly optimizes three complementary objectives: (i) unsupervised structure preservation via scalable modularity approximation, (ii) supervised regularization to minimize intra-class variance among labeled nodes, and (iii) semi-supervised propagation that refines unlabeled nodes through random-walk-based label spreading with attention-weighted similarity. These components are unified into a single iterative optimization scheme, yielding high-quality node embeddings. On standard benchmarks, our method consistently achieves classification accuracy at par with or superior to state-of-the-art approaches, while requiring significantly less computational cost. |
| title | FUSE: Fast Semi-Supervised Node Embedding Learning via Structural and Label-Aware Optimization |
| topic | Machine Learning I.5.2 |
| url | https://arxiv.org/abs/2510.11250 |