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

arXiv:2210.01301v3 Announce Type: replace
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.

abstract arxiv cs.lg cs.si diffusion feature graph link prediction network networks paper prediction spaces type