Proceedings

FS-KEN: Few-shot Knowledge Graph Reasoning by Adversarial Negative Enhancing

Lingyuan Meng, Ke Liang, Zeyu Zhu, Xinwang Liu, Wenpeng Lu

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 4597-4605.

https://doi.org/10.24963/ijcai.2025/512

Keywords

  • Computer Vision: CV: Structural and model-based approaches, knowledge representation and reasoning
  • Knowledge Representation and Reasoning: KRR: Learning and reasoning
  • Machine Learning: ML: Few-shot learning

Abstract

Few-shot knowledge graph reasoning (FS-KGR) try to infer missing facts in a knowledge graphs using limited data (such as only 3/5 samples).Existing strategies have shown good performance by mining more supervised information for few-shot learning through meta-learning and self-supervised learning. However, the problem of insufficient samples has not been fundamentally solved. In this paper, we propose a novel algorithm based on adversarial learning for Enhancing Negative samples in few-shot scenarios of FS-KGR, termed FS-KEN. Specifically, we are the first to use GAN to conduct data augmentation on FS-KGR scenario. FS-KEN uses policy gradient GANs for negative sample augmentation, solving the gradient back-propagation issue in traditional GANs. The generator aims to produce high-quality negative entities. while the objective of the discriminator is to distinguish between generated entities and real entities. Comprehensive experiments conducted on two few-shot knowledge graph completion datasets reveal that FS-KEN surpasses other baseline models, achieving state-of-the-art results.

Lingyuan Meng, Ke Liang, Zeyu Zhu, Xinwang Liu, and Wenpeng Lu. 2025. FS-KEN: Few-shot Knowledge Graph Reasoning by Adversarial Negative Enhancing. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 4597–4605. https://doi.org/10.24963/ijcai.2025/512
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards