AHP：学习负样本用于超边缘预测
AHP: Learning to Negative Sample for Hyperedge Prediction
摘要：
Hypergraphs（即，超边集）自然地表示组关系（例如，共同创作论文的研究人员和在食谱中一起使用的成分），其中每一个对应于一个超边缘（即，节点的子集）。预测未来或缺失的超边对许多应用具有重要意义（例如，合作和食谱推荐）。使超边缘预测特别具有挑战性的是大量的非超边缘子集，其随着节点的数量呈指数增长。由于禁止将所有这些都用作模型训练的负例，因此不可避免地要对其中的一小部分进行采样，为此，采用了启发式采样方案。然而，训练的模型遭受不同性质的例子的泛化能力差。在本文中，我们提出了AHP，一个基于对抗训练的超边缘预测方法。它学会了在不依赖任何启发式方案的情况下对负面示例进行采样。使用六个真正的超图，我们表明，层次分析法更好地推广到各种性质的负面例子。它产生的AUROC比现有的最佳方法高出28.2%，并且通常甚至优于其变体，其抽样方案针对测试集。
英文摘要：
Hypergraphs (i.e., sets of hyperedges) naturally represent group relations (e.g., researchers co-authoring a paper and ingredients used together in a recipe), each of which corresponds to a hyperedge (i.e., a subset of nodes). Predicting future or missing hyperedges bears significant implications for many applications (e.g., collaboration and recipe recommendation). What makes hyperedge prediction particularly challenging is the vast number of non-hyperedge subsets, which grows exponentially with the number of nodes. Since it is prohibitive to use all of them as negative examples for model training, it is inevitable to sample a very small portion of them, and to this end, heuristic sampling schemes have been employed. However, trained models suffer from poor generalization capability for examples of different natures. In this paper, we propose AHP, an adversarial training-based hyperedge-prediction method. It learns to sample negative examples without relying on any heuristic schemes. Using six real hypergraphs, we show that AHP generalizes better to negative examples of various natures. It yields up to 28.2% higher AUROC than the best existing methods and often even outperforms its variants with sampling schemes tailored to test sets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
