Litcius/Paper detail

Performance-Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks

Minji Yoon, Théophile Gervet, Baoxu Shi, Sufeng Niu, Qi He, Jaewon Yang

202129 citationsDOIOpen Access PDF

Abstract

The main challenge of adapting Graph convolutional networks (GCNs) to large-scale graphs is the scalability issue due to the uncontrollable neighborhood expansion in the aggregation stage. Several sampling algorithms have been proposed to limit the neighborhood expansion. However, these algorithms focus on minimizing the variance in sampling to approximate the original aggregation. This leads to two critical problems: 1) low accuracy because the sampling policy is agnostic to the performance of the target task, and 2) vulnerability to noise or adversarial attacks on the graph.

Topics & Concepts

Computer scienceScalabilityAdaptive samplingGraphSampling (signal processing)Focus (optics)AlgorithmAdversarial systemVariance (accounting)Artificial intelligenceTheoretical computer scienceMathematicsStatisticsAccountingComputer visionOpticsMonte Carlo methodDatabaseBusinessFilter (signal processing)PhysicsAdvanced Graph Neural NetworksAdversarial Robustness in Machine LearningDomain Adaptation and Few-Shot Learning
Performance-Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks | Litcius