Novel dropout approach for mitigating over-smoothing in graph neural networks
- 21 January 2025
- journal article
- research article
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (5) , 1-14
Abstract
No abstract availableKeywords
This publication has 24 references indexed in Scilit:
- Taming over-smoothing representation on heterophilic graphsInformation Sciences, 2023
- DropAGG: Robust Graph Neural Networks via Drop AggregationNeural Networks, 2023
- A Multi-objective Optimization Model for Redundancy Reduction in Convolutional Neural NetworksNeural Processing Letters, 2023
- An adaptive Drop method for deep neural networks regularization: Estimation of DropConnect hyperparameter using generalization gapKnowledge-Based Systems, 2022
- Complex graph convolutional network for link prediction in knowledge graphsExpert Systems with Applications, 2022
- Augmented Graph Neural Network with hierarchical global-based residual connectionsNeural Networks, 2022
- KRR-CNN: kernels redundancy reduction in convolutional neural networksNeural Computing and Applications, 2021
- STGSN — A Spatial–Temporal Graph Neural Network framework for time-evolving social networksKnowledge-Based Systems, 2021
- Building a PubMed knowledge graphScientific Data, 2020
- Graph Representation Learning2020