Heterogeneous Graph Neural Networks (HGNNs) are a class of deep learning
models designed specifically for heterogeneous graphs, which are graphs that
contain different types of nodes and edges. This paper investigates the
application of curriculum learning techniques to improve the performance and
robustness of Heterogeneous Graph Neural Networks (GNNs). To better classify
the quality of the data, we design a loss-aware training schedule, named LTS
that measures the quality of every nodes of the data and incorporate the
training dataset into the model in a progressive manner that increases
difficulty step by step. LTS can be seamlessly integrated into various
frameworks, effectively reducing bias and variance, mitigating the impact of
noisy data, and enhancing overall accuracy. Our findings demonstrate the
efficacy of curriculum learning in enhancing HGNNs capabilities for analyzing
complex graph-structured data. The code is public at https:
//github.com/LARS-research/CLGNN/.

本文研究异构图神经网络 (HGNNs) 的课程学习技术应用，设计了一种损失感知的训练进度表，命名为 LTS，该表度量数据的每个节点的质量，并逐步增加难度地将训练数据集融入模型中。LTS 可无缝集成到各种框架中，有效减少偏差和方差，减轻噪声数据的影响，并提高整体准确性，从而展示了课程学习在增强 HGNNs 分析复杂图结构数据能力方面的功效。

基于损失感知的异构图神经网络课程学习

Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks

Graph Neural Networks (GNNs) have shown success in various fields for
learning from graph-structured data. This paper investigates the application of
ensemble learning techniques to improve the performance and robustness of Graph
Neural Networks (GNNs). By training multiple GNN models with diverse
initializations or architectures, we create an ensemble model named ELGNN that
captures various aspects of the data and uses the Tree-Structured Parzen
Estimator algorithm to determine the ensemble weights. Combining the
predictions of these models enhances overall accuracy, reduces bias and
variance, and mitigates the impact of noisy data. Our findings demonstrate the
efficacy of ensemble learning in enhancing GNN capabilities for analyzing
complex graph-structured data. The code is public at
this https URL

本研究探讨了集成学习技术在改善图神经网络（GNNs）性能和鲁棒性方面的应用。我们通过使用多种不同的初始化或结构来训练多个 GNN 模型，创建了一个名为 ELGNN 的集成模型，该模型捕捉了数据的各个方面，并使用树状结构 Parzen 估计算法确定集成权重。结合这些模型的预测结果可以提高整体准确性，减少偏差和方差，并减轻噪声数据的影响。我们的研究结果证明了集成学习在提升 GNN 对分析复杂图结构数据的能力方面的有效性。