Heterogeneous Graph Sparsification for Efficient Representation Learning
Graph sparsification is a powerful tool to approximate an arbitrary graph and has been used in machine learning over homogeneous graphs. In heterogeneous graphs such as knowledge graphs, however, sparsification has not been systematically exploited to improve efficiency of learning tasks. In this work, we initiate the study on heterogeneous graph sparsification and develop sampling-based algorithms for constructing sparsifiers that are provably sparse and preserve important information in the original graphs. We have performed extensive experiments to confirm that the proposed method can improve time and space complexities of representation learning while achieving comparable, or even better performance in subsequent graph learning tasks based on the learned embedding.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph LearningKnowledge GraphsRepresentation LearningSimilar Papers 제목 키워드 기반
Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning
Predictive systems increasingly span heterogeneous modalities such as graphs, language, and tabular records, but sparsity and efficiency remain modality-specific (graph edge or neighborhood sparsification, Transformer he…
Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks
Spectral graph sparsification is a classical tool for reducing graph complexity while preserving Laplacian quadratic forms. In graph neural networks (GNNs), sparsification is often used to accelerate computation while ma…
Long-term Visual Map Sparsification with Heterogeneous GNN
We address the problem of map sparsification for long-term visual localization. For map sparsification, a commonly employed assumption is that the pre-build map and the later captured localization query are consistent. H…
Graph Neural NetworkVisual LocalizationmyAURA: Personalized health library for epilepsy management via knowledge graph sparsification and visualization
Objective: We report the development of the patient-centered myAURA application and suite of methods designed to aid epilepsy patients, caregivers, and researchers in making decisions about care and self-management. Mate…
ManagementRobust Graph Representation Learning via Neural Sparsification
Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection. Real-life graphs usually have complex information in the local neighborhood, where e…
Fraud DetectionGraph Representation LearningNode ClassificationProduct Recommendation+1