图形神经网络与粗粒和细粒区分,以减轻标签噪声和稀疏性
Shuangjie Li1, Baoming Zhang1, Jianqing Song1
1State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China; Department of Computer Science and Technology, Nanjing University, Nanjing, 210023, China.
概括
本研究介绍了GNN-CFGD,这是一种新的图形神经网络方法,用于改善带有噪音和稀疏标签的图形的半监督学习. GNN-CFGD有效地区分清洁和噪音标签,提高节点分类的准确性.
科学领域:
- 机器学习 机器学习
- 图形神经网络的神经网络
- 数据挖掘 数据挖掘
背景情况:
- 图形神经网络 (GNN) 在半监督学习方面表现出色,但在杂和稀疏的标签上扎.
- 现实世界的图形数据经常存在标签缺陷,降低了GNN的性能.
- 强大的GNN对于将节点分类为标签噪声至关重要.
研究的目的:
- 提出GNN-CFGD,一种新的GNN架构,以减轻标签稀疏性和噪音.
- 在图表上提高半监督节点分类的稳定性.
- 在实际的,不完美的标签场景中提高GNN性能.
主要方法:
- 开发了GNN-CFGD,使用粗粒和细粒标签划分和图形重建.
- 采用高斯混合模型 (GMM) 具有记忆效应来识别干净的标签.
- 引入了以清洁标签为导向的链接,以将未标记的节点连接到清洁的节点.
- 基于对精细监督的信任的细粒度杂和未标记的节点.
主要成果:
- 证明将未标记的节点连接到清洁标签对噪声更有效.
- 通过其分工战略,GNN-CFGD有效地减少了噪音标签的影响.
- 实验表明GNN-CFGD在各种数据集中的卓越有效性和稳定性.
结论:
- GNN-CFGD为带有噪音和稀疏标签的半监督节点分类提供了一个强大的解决方案.
- 拟议的粗粒和细粒区分策略显著提高了GNN的性能.
- 这项工作解决了将GNN应用于现实世界的图形数据的关键挑战.
更多相关视频
03:31Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
449
11:24Targeted Labeling of Neurons in a Specific Functional Micro-domain of the Neocortex by Combining Intrinsic Signal and Two-photon Imaging
Published on: December 12, 2012
13.6K
相关概念视频
01:29Aggregates Classification
297
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
297
01:30Classification of Signals
369
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
369
01:18Reducing Line Loss
141
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
141