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

no code implementations • 10 Mar 2024 • Pengfei Ding, Yan Wang, Guanfeng Liu

In this paper, we provide a comprehensive review of existing FLHG methods, covering challenges, research progress, and future prospects.

Few-Shot Learning

Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphs

no code implementations • 7 Jan 2024 • Pengfei Ding, Yan Wang, Guanfeng Liu, Nan Wang, Xiaofang Zhou

To address this challenging problem, we propose a novel Causal OOD Heterogeneous graph Few-shot learning model, namely COHF.

Few-Shot Learning Out-of-Distribution Generalization +2

Cross-heterogeneity Graph Few-shot Learning

no code implementations • 10 Aug 2023 • Pengfei Ding, Yan Wang, Guanfeng Liu

In recent years, heterogeneous graph few-shot learning has been proposed to address the label sparsity issue in heterogeneous graphs (HGs), which contain various types of nodes and edges.

Few-Shot Learning Informativeness

Few-Shot Semantic Relation Prediction across Heterogeneous Graphs

no code implementations • 11 Jul 2022 • Pengfei Ding, Yan Wang, Guanfeng Liu, Xiaofang Zhou

In real-world scenarios, new semantic relations constantly emerge and they typically appear with only a few labeled data.

Meta-Learning Relation