Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks

2024/02/29 by Zhen Hao Wong, Hansi Yang, Wong, Zhen Hao +5
Computer Science · Neuroscience · #Advanced Graph Neural Networks #Brain Tumor Detection and Classification #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2402.18875

openalex publication_date 2024/02/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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/.

Related

• Heterogeneous Graph Neural Networks with Loss-decrease-aware Curriculum Learning
• Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First
• Graph Neural Network with Curriculum Learning for Imbalanced Node Classification
• MentorGNN: Deriving Curriculum for Pre-Training GNNs
• Heta: Distributed Training of Heterogeneous Graph Neural Networks