# AHP: Learning to Negative Sample for Hyperedge Prediction

arXiv: https://arxiv.org/abs/2204.06353 · HTML: https://mlsanity.com/paper/2204.06353/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 13 Apr 2022.

## Builds on (most cited first, 23 of 23)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [Stabilizing Training of Generative Adversarial Networks through Regularization](https://mlsanity.com/paper/1705.09367/) (2017)
- [HNHN: Hypergraph Networks with Hyperedge Neurons](https://mlsanity.com/paper/2006.12278/) (2020)
- [Simplicial Closure and higher-order link prediction](https://mlsanity.com/paper/1802.06916/) (2018)
- [Hyper-SAGNN: a self-attention based graph neural network for hypergraphs](https://mlsanity.com/paper/1911.02613/) (2019)
- [Structural Deep Embedding for Hyper-Networks](https://mlsanity.com/paper/1711.10146/) (2017)
- [Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation](https://mlsanity.com/paper/2109.04200/) (2021)
- [Clustering in graphs and hypergraphs with categorical edge labels](https://mlsanity.com/paper/1910.09943/) (2019)
- [How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction](https://mlsanity.com/paper/2001.11181/) (2020)
- [Structural Patterns and Generative Models of Real-world Hypergraphs](https://mlsanity.com/paper/2006.07060/) (2020)
- [The why, how, and when of representations for complex systems](https://mlsanity.com/paper/2006.02870/) (2020)
- [How Do Hyperedges Overlap in Real-World Hypergraphs? -- Patterns, Measures, and Generators](https://mlsanity.com/paper/2101.07480/) (2021)
- [Hyperbolic Hypergraphs for Sequential Recommendation](https://mlsanity.com/paper/2108.08134/) (2021)
- [Hypergraph Motifs: Concepts, Algorithms, and Discoveries](https://mlsanity.com/paper/2003.01853/) (2020)
- [Evolution of Real-world Hypergraphs: Patterns and Models without Oracles](https://mlsanity.com/paper/2008.12729/) (2020)
- [Click-Through Rate Prediction with Multi-Modal Hypergraphs](https://mlsanity.com/paper/2109.02398/) (2021)
- [Hypergraph Ego-networks and Their Temporal Evolution](https://mlsanity.com/paper/2112.03498/) (2021)
- [THyMe+: Temporal Hypergraph Motifs and Fast Algorithms for Exact Counting](https://mlsanity.com/paper/2109.08341/) (2021)
- [On the Persistence of Higher-Order Interactions in Real-World Hypergraphs](https://mlsanity.com/paper/2201.00972/) (2022)

## Built on by (most cited first, 12 of 12)

- [A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide](https://mlsanity.com/paper/2404.01039/) (2024)
- [A Survey on Hyperlink Prediction](https://mlsanity.com/paper/2207.02911/) (2022)
- [DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning](https://mlsanity.com/paper/2508.12244/) (2025)
- [HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction](https://mlsanity.com/paper/2502.05827/) (2025)
- [Enhancing Hyperedge Prediction with Context-Aware Self-Supervised Learning](https://mlsanity.com/paper/2309.05798/) (2023)
- [ChemHGNN: A Hierarchical Hypergraph Neural Network for Reaction Virtual Screening and Discovery](https://mlsanity.com/paper/2506.11041/) (2025)
- [On the Power of Graph Neural Networks and Feature Augmentation Strategies to Classify Social Networks](https://mlsanity.com/paper/2401.06048/) (2024)
- [Hyperedge Anomaly Detection with Hypergraph Neural Network](https://mlsanity.com/paper/2412.05641/) (2024)
- [Tensor Convolutional Network for Higher-Order Interaction Prediction in Sparse Tensors](https://mlsanity.com/paper/2503.11786/) (2025)
- [Learning Short-Term and Long-Term Patterns of High-Order Dynamics in Real-World Networks](https://mlsanity.com/paper/2508.17236/) (2025)
- [Identifying Group Anchors in Real-World Group Interactions Under Label Scarcity](https://mlsanity.com/paper/2509.20762/) (2025)
- [HyperSearch: Prediction of New Hyperedges through Unconstrained yet Efficient Search](https://mlsanity.com/paper/2510.17153/) (2025)

## Abstract (arXiv)

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.