GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction

2022/10/04 by Zixiao Wang, Yuluo Guo, Wang, Zixiao +13 · 1 citation
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Caching and Content Delivery #Complex Network Analysis Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Social and Information Networks (cs.SI)

paper · pdf · doi:10.48550/arxiv.2210.01301

openalex publication_date 2022/10/04 · openalex created_date 2022/10/06 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model. This model generalizes graph diffusion in different feature spaces, and uses the inception module to avoid the large amount of computations caused by complex network structures. We evaluate GIDN model on Open Graph Benchmark(OGB) datasets, reached an 11% higher performance than AGDN on ogbl-collab dataset.

Cited by

• OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction

Related

• Graph Diffusion-Embedding Networks
• NodeSig: Binary Node Embeddings via Random Walk Diffusion
• Benchmarking Graph Neural Networks on Link Prediction
• Node-wise Diffusion for Scalable Graph Learning
• Demystifying Distributed Training of Graph Neural Networks for Link Prediction