Improved large-scale graph learning through ridge spectral sparsification
arXiv:2604.20078
Abstract
Graph-based techniques and spectral graph theory have enriched the field of machine learning with a variety of critical advances. A central object in the analysis is the graph Laplacian L, which encodes the structure of the graph. We consider the problem of learning over this Laplacian in a distributed streaming setting, where new edges of the graph are observed in real time by a network of workers. In this setting, it is hard to learn quickly or approximately while keeping a distributed representation of L. To address this challenge, we present a novel algorithm, GSQUEAK, which efficiently sparsifies the Laplacian by maintaining a small subset of effective resistances. We show that our algorithm produces sparsifiers with strong spectral approximation guarantees, all while processing edges in a single pass and in a distributed fashion.
International Conference on Machine Learning (ICML 2018)
Cited by in corpus (8)
- A Gentle Introduction to Deep Learning for Graphs
- A Unified Lottery Ticket Hypothesis for Graph Neural Networks
- Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification
- Graph reduction with spectral and cut guarantees
- Slim Graph: Practical Lossy Graph Compression for Approximate Graph Processing, Storage, and Analytics
- A Survey on Large-scale Machine Learning
- LSP : Acceleration and Regularization of Graph Neural Networks via Locality Sensitive Pruning of Graphs
- Learnt Sparsification for Interpretable Graph Neural Networks