Few-shot Learning on Heterogeneous Graphs: Challenges, Progress, and Prospects

2024/03/10 by Pengfei Ding, Yan Wang, Ding, Pengfei +3
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM

paper · pdf · doi:10.48550/arxiv.2403.13834

openalex publication_date 2024/03/10 · openalex created_date 2024/03/24 · openalex updated_date 2026/07/28

Abstract

Few-shot learning on heterogeneous graphs (FLHG) is attracting more attention from both academia and industry because prevailing studies on heterogeneous graphs often suffer from label sparsity. FLHG aims to tackle the performance degradation in the face of limited annotated data and there have been numerous recent studies proposing various methods and applications. In this paper, we provide a comprehensive review of existing FLHG methods, covering challenges, research progress, and future prospects. Specifically, we first formalize FLHG and categorize its methods into three types: single-heterogeneity FLHG, dual-heterogeneity FLHG, and multi-heterogeneity FLHG. Then, we analyze the research progress within each category, highlighting the most recent and representative developments. Finally, we identify and discuss promising directions for future research in FLHG. To the best of our knowledge, this paper is the first systematic and comprehensive review of FLHG.

Related

• Cross-heterogeneity Graph Few-shot Learning
• A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning
• Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphs
• Few-Shot Learning on Graphs
• FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs