Grale: Designing Networks For Graph Learning

Abstract

How can we find the right graph for semi-supervised learning? In real world applications, the choice of which edges to use for computation is the first step in any graph learning process. Interestingly, there are often many types of similarity available to choose as the edges between nodes, and the choice of edges can drastically affect the performance of downstream semi-supervised learning systems. However, despite the importance of graph design, most of the literature assumes that the graph is static. In this work, we present Grale, a scalable method we have developed to address the problem of graph design for graphs with billions of nodes. Grale operates by fusing together different measures of(potentially weak) similarity to create a graph which exhibits high task-specific homophily between its nodes. Grale is designed for running on large datasets. We have deployed Grale in more than 20 different industrial settings at Google, including datasets which have tens of billions of node

Stats

• citations27
• S2 citations—
• github stars0
• HF likes0
• heat score10.85
• arxiv keyhalcrow2020grale

Related papers

• Large-scale Graph Building In Dynamic Environments: Low Latency And High Quality (2025)0.00
• Deep Graph Similarity Learning: A Survey (2019)13.97
• Large Scale Graph Learning From Smooth Signals (2017)0.00
• S\(^3\)GND: An Effective Learning-based Approach For Subgraph Similarity Search Under Generalized Neighbor Difference Semantics (technical Report) (2026)0.00
• Stars: Tera-scale Graph Building For Clustering And Graph Learning (2022)0.00
• Simgnn: A Neural Network Approach To Fast Graph Similarity Computation (2018)0.00
• SEGMN: A Structure-enhanced Graph Matching Network For Graph Similarity Learning (2024)2.26
• Towards Similarity Graphs Constructed By Deep Reinforcement Learning (2019)0.00