MILE: A Multi-Level Framework for Scalable Graph Embedding

Abstract

Recently there has been a surge of interest in designing graph embedding methods. Few, if any, can scale to a large-sized graph with millions of nodes due to both computational complexity and memory requirements. In this paper, we relax this limitation by introducing the MultI-Level Embedding (MILE) framework -- a generic methodology allowing contemporary graph embedding methods to scale to large graphs. MILE repeatedly coarsens the graph into smaller ones using a hybrid matching technique to maintain the backbone structure of the graph. It then applies existing embedding methods on the coarsest graph and refines the embeddings to the original graph through a graph convolution neural network that it learns. The proposed MILE framework is agnostic to the underlying graph embedding techniques and can be applied to many existing graph embedding methods without modifying them. We employ our framework on several popular graph embedding techniques and conduct embedding for real-world graphs. Experimental results on five large-scale datasets demonstrate that MILE significantly boosts the speed (order of magnitude) of graph embedding while generating embeddings of better quality, for the task of node classification. MILE can comfortably scale to a graph with 9 million nodes and 40 million edges, on which existing methods run out of memory or take too long to compute on a modern workstation. Our code and data are publicly available with detailed instructions for adding new base embedding methods: \url{https://github.com/jiongqian/MILE}.

arXiv commentAccepted in ICWSM 2021

References in corpus (12)

• Fast unfolding of communities in large networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Deep Convolutional Networks on Graph-Structured Data
• PyTorch-BigGraph: A Large-scale Graph Embedding System
• Role Discovery in Networks
• Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change
• HARP: Hierarchical Representation Learning for Networks
• SocialGCN: An Efficient Graph Convolutional Network based Model for Social Recommendation
• A Framework for Generalizing Graph-based Representation Learning Methods
• Principled Multilayer Network Embedding
• Network Representation Learning: Consolidation and Renewed Bearing

Cited by in corpus (10)

• PyTorch-BigGraph: A Large-scale Graph Embedding System
• Graph Clustering with Graph Neural Networks
• GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding
• Network Representation Learning: Consolidation and Renewed Bearing
• Parallel Computation of Graph Embeddings
• Initialization for Network Embedding: A Graph Partition Approach
• Graph Cross Networks with Vertex Infomax Pooling
• Diversified Multiscale Graph Learning with Graph Self-Correction
• Scaling Up Graph Neural Networks Via Graph Coarsening
• Toward Edge-Centric Network Embeddings