提出新方法生成更真实的负超边，提升高阶关系预测准确率
HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction
- 用正超边引导生成负超边，提高生成质量
- 引入正则项防止生成错误的负样本，避免误导训练
- 在6个真实超图上优于现有方法，适合关系预测任务
超边预测是基于已观察网络结构预测未来高阶关系的基本任务。现有方法面临数据稀疏问题，虽可通过负采样利用不存在的超边作为对比信息来缓解，但存在两大未被充分研究的挑战：(C1) 负样本生成缺乏指导，(C2) 可能产生虚假负样本。为此，我们提出 HyGEN 方法，采用 (1) 以正超边为指导生成更现实负超边的生成器，以及 (2) 防止生成超边成为虚假负样本的正则化项。在六个真实超图上的大量实验表明，HyGEN 持续优于四种最先进的超边预测方法。
原文摘要 · Abstract (English)
Hyperedge prediction is a fundamental task to predict future high-order relations based on the observed network structure. Existing hyperedge prediction methods, however, suffer from the data sparsity problem. To alleviate this problem, negative sampling methods can be used, which leverage non-existing hyperedges as contrastive information for model training. However, the following important challenges have been rarely studied: (C1) lack of guidance for generating negatives and (C2) possibility of producing false negatives. To address them, we propose a novel hyperedge prediction method, HyGEN, that employs (1) a negative hyperedge generator that employs positive hyperedges as a guidance to generate more realistic ones and (2) a regularization term that prevents the generated hyperedges from being false negatives. Extensive experiments on six real-world hypergraphs reveal that HyGEN consistently outperforms four state-of-the-art hyperedge prediction methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。