Diffwire: Inductive graph rewiring via the lov\'asz bound
Graph Neural Networks (GNNs) have been shown to achieve competitive results to tackle
graph-related tasks, such as node and graph classification, link prediction and node and …
graph-related tasks, such as node and graph classification, link prediction and node and …
Graph convolutional network soft sensor for process quality prediction
The nonlinear time-varying characteristics of the process industry can be modeled using
numerous data-driven soft sensor methods. However, the intrinsic relationships among the …
numerous data-driven soft sensor methods. However, the intrinsic relationships among the …
Laplacian canonization: A minimalist approach to sign and basis invariant spectral embedding
Spectral embedding is a powerful graph embedding technique that has received a lot of
attention recently due to its effectiveness on Graph Transformers. However, from a …
attention recently due to its effectiveness on Graph Transformers. However, from a …
Pyramid graph neural network: A graph sampling and filtering approach for multi-scale disentangled representations
Spectral methods for graph neural networks (GNNs) have achieved great success. Despite
their success, many works have shown that existing approaches are mainly focused on low …
their success, many works have shown that existing approaches are mainly focused on low …
A dynamic spatial distributed information clustering method for aluminum electrolysis cell
Y Sun, W Gui, X Chen, Y Xie, S Xie, Z Zou - Engineering Applications of …, 2023 - Elsevier
Distributed anode current (DAC) is a high-dimensional spatial-distributed signal that can be
measured online in the industrial aluminum electrolysis process. The difference of …
measured online in the industrial aluminum electrolysis process. The difference of …
Perturbation-augmented graph convolutional networks: A graph contrastive learning architecture for effective node classification tasks
Q Guo, X Yang, F Zhang, T Xu - Engineering Applications of Artificial …, 2024 - Elsevier
In the context of recent advances in Graph Convolutional Networks (GCNs) for semi-
supervised learning, a significant highlight is the potential of Graph Contrastive Learning …
supervised learning, a significant highlight is the potential of Graph Contrastive Learning …
Multi-Agent Safe Graph Reinforcement Learning for PV Inverters-Based Real-Time Decentralized Volt/Var Control in Zoned Distribution Networks
To realize real-time voltage/var control (VVC) in active distribution networks (ADNs), this
paper proposes a new multi-agent safe graph reinforcement learning method to optimize …
paper proposes a new multi-agent safe graph reinforcement learning method to optimize …
Towards self-explainable graph convolutional neural network with frequency adaptive inception
F Wei, K Mei - Pattern Recognition, 2024 - Elsevier
Graph convolutional neural networks (GCNs) have demonstrated powerful representing
ability of irregular data, eg, skeletal data and graph-structured data, providing the effective …
ability of irregular data, eg, skeletal data and graph-structured data, providing the effective …
Revisiting graph-based fraud detection in sight of heterophily and spectrum
F Xu, N Wang, H Wu, X Wen, X Zhao… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Graph-based fraud detection (GFD) can be regarded as a challenging semi-supervised
node binary classification task. In recent years, Graph Neural Networks (GNN) have been …
node binary classification task. In recent years, Graph Neural Networks (GNN) have been …
A dynamic graph structure identification method of spatio-temporal correlation in an aluminum electrolysis cell
Y Sun, X Chen, L Cen, W Gui, C Yang, Z Zou - Applied Soft Computing, 2024 - Elsevier
The dynamic correlation analysis of cell-spatial information (distributed anode current signal,
DACS) is of great significance in the regional-refined control of industrial aluminum …
DACS) is of great significance in the regional-refined control of industrial aluminum …