GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction
Preprint
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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Line Graph Neural Networks for Link PredictionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- A Survey on Knowledge Graphs: Representation, Acquisition, and ApplicationsIEEE Transactions on Neural Networks and Learning Systems, 2021
- SMR: Medical Knowledge Graph Embedding for Safe Medicine RecommendationBig Data Research, 2021
- Named Entity Extraction for Knowledge Graphs: A Literature OverviewIEEE Access, 2020
- Faceted search over RDF-based knowledge graphsJournal of Web Semantics, 2016
- A Review of Relational Machine Learning for Knowledge GraphsProceedings of the IEEE, 2015
- Reprint of: The anatomy of a large-scale hypertextual web search engineComputer Networks, 2012
- Link prediction in complex networks: A surveyPhysica A: Statistical Mechanics and its Applications, 2011
- Predicting missing links via local informationThe European Physical Journal B, 2009
- Hybrid Search: Effectively Combining Keywords and Semantic Searches2008