HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929298960547840 |
|---|---|
| author | Zhang, Yue He, Yuntian Gurukar, Saket Parthasarathy, Srinivasan |
| author_facet | Zhang, Yue He, Yuntian Gurukar, Saket Parthasarathy, Srinivasan |
| contents | Heterogeneous graphs are ubiquitous in real-world applications because they can represent various relationships between different types of entities. Therefore, learning embeddings in such graphs is a critical problem in graph machine learning. However, existing solutions for this problem fail to scale to large heterogeneous graphs due to their high computational complexity. To address this issue, we propose a Multi-Level Embedding framework of nodes on a heterogeneous graph (HeteroMILE) - a generic methodology that allows contemporary graph embedding methods to scale to large graphs. HeteroMILE repeatedly coarsens the large sized graph into a smaller size while preserving the backbone structure of the graph before embedding it, effectively reducing the computational cost by avoiding time-consuming processing operations. It then refines the coarsened embedding to the original graph using a heterogeneous graph convolution neural network. We evaluate our approach using several popular heterogeneous graph datasets. The experimental results show that HeteroMILE can substantially reduce computational time (approximately 20x speedup) and generate an embedding of better quality for link prediction and node classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00816 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs Zhang, Yue He, Yuntian Gurukar, Saket Parthasarathy, Srinivasan Machine Learning Artificial Intelligence Heterogeneous graphs are ubiquitous in real-world applications because they can represent various relationships between different types of entities. Therefore, learning embeddings in such graphs is a critical problem in graph machine learning. However, existing solutions for this problem fail to scale to large heterogeneous graphs due to their high computational complexity. To address this issue, we propose a Multi-Level Embedding framework of nodes on a heterogeneous graph (HeteroMILE) - a generic methodology that allows contemporary graph embedding methods to scale to large graphs. HeteroMILE repeatedly coarsens the large sized graph into a smaller size while preserving the backbone structure of the graph before embedding it, effectively reducing the computational cost by avoiding time-consuming processing operations. It then refines the coarsened embedding to the original graph using a heterogeneous graph convolution neural network. We evaluate our approach using several popular heterogeneous graph datasets. The experimental results show that HeteroMILE can substantially reduce computational time (approximately 20x speedup) and generate an embedding of better quality for link prediction and node classification. |
| title | HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2404.00816 |