graph neural networks

A framework for brain tumor (Glioma) analysis using SVM and graph convolutional networks

##基于图卷积神经网络的社交网络舆情分析

This paper investigates the application of Graph Convolutional Neural Networks (GCNs) for social network sentiment analysis. Traditional methods for analyzing public opinion often struggle with the complex, interconnected nature of social networks and the dynamic patterns of information dissemination. This research pro...

Title: Graph-Based Machine Learning Knowledge Distillation

Knowledge distillation is a technique for transferring knowledge from a large, complex model to a smaller, more efficient model. This paper presents a novel graph-based knowledge distillation method that leverages the inherent structure of neural networks to effectively transfer knowledge. We demonstrate that the use o...

Contextual Graph Neural Networks with Episodic Memory

This paper introduces Contextual Graph Neural Networks (CGNNs) with Episodic Memory, a novel approach to graph representation learning that addresses the limitations of standard Graph Neural Networks (GNNs) in handling contextual information across multiple graph instances. The core claim is that conventional GNNs stru...

A semi-supervised graph learning approach based on dual-stream gated fusion for industry equipment fault diagnosis under extreme label scarcity

This paper proposes the dual-stream gated fusion network coupled with a label propagation system (DSGF-LPS), a semi-supervised graph learning framework integrating robust graph construction, label propagation, and dual-stream gated fusion.

Neuro-Symbolic Reasoning with Attention-Based Knowledge Graphs

This paper proposes a novel approach to neuro-symbolic reasoning that addresses the challenges of seamless integration between neural networks and symbolic knowledge graphs. The core idea is to introduce an attention mechanism within the neural network architecture, allowing it to dynamically select and prioritize rele...

Dynamic Adaptive Graph Neural Networks: A Novel Approach to Graph Representation and Reasoning

Dynamic Adaptive Graph Neural Networks (D-AGNNs) represent a significant advancement in graph neural network design, focusing on the ability to dynamically adjust the graph structure to optimize both representation and reasoning capabilities. This paper introduces a novel algorithmic framework, leveraging adaptive algo...

Dynamic Graph-Based Machine Learning Algorithm

This paper introduces a novel machine learning algorithm, termed the Dynamic Graph-Based Machine Learning Algorithm, designed to enhance the performance of graph neural networks (GNNs) through adaptive graph structure learning. Traditional GNN approaches often rely on pre-defined graph structures, limiting their applic...

SAFM-Net: a dual-branch CNN–GNN network with synergistic attention and frequency-domain modulation for ultrasound thyroid nodule segmentation

SA-Net, a dual-branch CNN–GNN Network that integrates synergistic attention and frequency-domain modulation, provides accurate and robust segmentation performance under challenging ultrasound imaging conditions.

基于图的图神经网络的自适应学习

This paper introduces a novel self-adaptive learning method for graph neural networks (GNNs). Traditional GNNs often rely on fixed architectures, limiting their ability to adapt to evolving data landscapes. We propose a method that dynamically adjusts the graph structure of the network during training, leveraging the i...

自适应图神经网络的图结构调整

This paper introduces a novel algorithm for graph neural network (GNN) graph structure adjustment, leveraging the principles of adaptive neural networks. Traditional approaches often struggle with fixed parameter settings, limiting the model's ability to effectively capture complex relationships within the data. Our pr...

Graph Neural Networks for Software Dependency Discovery

This paper explores the application of Graph Neural Networks (GNNs) for automated software dependency discovery. Traditional methods for identifying dependencies rely heavily on manual annotation or rule-based approaches, often proving insufficient in complex software systems. We propose a novel approach that leverages...