HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs
This addresses scalability issues for researchers and practitioners working with large heterogeneous graphs in applications like social networks or recommendation systems, though it is incremental as it builds on existing embedding methods.
The paper tackles the problem of scaling graph embedding methods to large heterogeneous graphs by proposing HeteroMILE, a multi-level framework that coarsens graphs to reduce computational cost and refines embeddings, achieving approximately 20x speedup and improved embedding quality for link prediction and node classification.
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.