Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks
This work addresses the challenge of noisy data and bias in heterogeneous graph analysis for researchers and practitioners in graph machine learning, representing an incremental improvement.
The paper tackles the problem of improving performance and robustness in Heterogeneous Graph Neural Networks (HGNNs) by applying curriculum learning with a loss-aware training schedule (LTS), resulting in enhanced accuracy and reduced bias and variance.
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/.