EDGE++: Improved Training and Sampling of EDGE

TL;DR

This paper enhances the EDGE graph generation model by introducing a degree-specific noise schedule and an improved sampling scheme, resulting in more efficient and accurate large graph synthesis.

Contribution

It proposes novel modifications to EDGE, including a degree-specific noise schedule and a refined sampling process, improving efficiency and accuracy in large graph generation.

Findings

Reduced memory consumption through degree-specific noise scheduling

Enhanced control over generated graph similarity

Improved efficiency and accuracy in graph synthesis

Abstract

Recently developed deep neural models like NetGAN, CELL, and Variational Graph Autoencoders have made progress but face limitations in replicating key graph statistics on generating large graphs. Diffusion-based methods have emerged as promising alternatives, however, most of them present challenges in computational efficiency and generative performance. EDGE is effective at modeling large networks, but its current denoising approach can be inefficient, often leading to wasted computational resources and potential mismatches in its generation process. In this paper, we propose enhancements to the EDGE model to address these issues. Specifically, we introduce a degree-specific noise schedule that optimizes the number of active nodes at each timestep, significantly reducing memory consumption. Additionally, we present an improved sampling scheme that fine-tunes the generative process, allowing for better control over the similarity between the synthesized and the true network. Our experimental results demonstrate that the proposed modifications not only improve the efficiency but also enhance the accuracy of the generated graphs, offering a robust and scalable solution for graph generation tasks.