Skip to content
Log in
#graph neural networks Open access

基于自适应的图神经网络网络

Jincheng Zhang
Aug 2026 · Zenodo (CERN European Organization for Nuclear Research)
Advanced Graph Neural Networks

Abstract

This paper presents a novel approach to graph neural networks (GNNs) based on adaptive graph structures. Traditional GNNs often employ static graph structures, limiting their ability to effectively capture complex relationships within the data. This research introduces a dynamic graph structure adjustment mechanism, dynamically optimizing the graph topology during training. This adaptation allows the model to generalize better to unseen data and improve the representation of intricate patterns within the input graph. The proposed method addresses limitations in current GNN architectures by enabling robust and adaptable learning, ultimately enhancing the model's performance and robustness. We demonstrate the effectiveness of this approach through extensive experiments on benchmark datasets, showcasing significant improvements in both accuracy and generalization ability compared to existing GNN methods.

DOI
View source

Similar papers

#graph neural networks Oct 2026

Locality-Preserving Graph Laplacian Manifold Learning Based Model Predictive Control for Three-Phase Inverters

This article presents a model predictive control (MPC) strategy for three-phase inverters based on locality preserving projections (LPPs). Unlike conventional machine learning–based MPC approaches that rely on predefined or high-dimensional input features, the proposed LPP-MPC automatically extracts compact, informative representations by preserving the data’s intrinsic geometric structure. This dimensionality reduction enables fast linear control-law evaluation with computational complexity O(1), making the controller well-suited for real-time implementation. Experimental results demonstrate that the LPP-MPC achieves lower total harmonic distortion (THD) and reduced tracking error compared to quadratic-programming MPC under both linear and nonlinear load conditions, and the proposed controller maintains consistently lower THD throughout load transients than other methods such as two-degree-of-freedom MPC. Compared to existing model-free MPC and deep learning neural network, the LPP-MPC has the lowest THD and root mean square error with the least computational time owing to its efficient linear structure and strong generalization capability.

Jianwu Zeng, Lizheng Cheng, V. Winstead et al. · 1 citation

Related blog posts