Non-Homophily

A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness
A comprehensive benchmark on spectral GNNs relating efficiency and effectiveness.
A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness
Scalable Heterophilous Graph Neural Network with Decoupled Embeddings
We propose LD² as a scalable heterophilous GNN with linear complexity and lightweight minibatch training.
Jul 31, 2024 14:45 — 15:00 SMU, Singapore
Scalable Heterophilous Graph Neural Network with Decoupled Embeddings
LD²: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings
A scalable heterophilous GNN with lightweight minibatch training.
LD²: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings