AHP: Learning to Negative Sample for Hyperedge Prediction
- URL: http://arxiv.org/abs/2204.06353v1
- Date: Wed, 13 Apr 2022 13:09:35 GMT
- Title: AHP: Learning to Negative Sample for Hyperedge Prediction
- Authors: Hyunjin Hwang, Seungwoo Lee, Chanyoung Park, and Kijung Shin
- Abstract summary: We propose AHP, an adversarial training-based hyperedge-prediction method.
It learns to sample negative examples without relying on any schemes.
It yields up to 28.2% higher AUROC than best existing methods.
- Score: 14.830450801473459
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: 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 implication 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 best existing methods and often even outperforms its
variants with sampling schemes tailored to test sets.
Related papers
- HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction [16.673776336773738]
Hyperedge prediction is a fundamental task to predict future high-order relations based on observed network structure.
Existing hyperedge prediction methods, however, suffer from the data sparsity problem.
We propose a novel hyperedge prediction method, HyGEN, that employs a negative hyperedge generator that employs positive hyperedges as a guidance to generate more realistic ones.
arXiv Detail & Related papers (2025-02-09T09:27:35Z) - Scalable and Effective Negative Sample Generation for Hyperedge Prediction [55.9298019975967]
Hyperedge prediction is crucial for understanding complex multi-entity interactions in web-based applications.
Traditional methods often face difficulties in generating high-quality negative samples due to imbalance between positive and negative instances.
We present the scalable and effective negative sample generation for Hyperedge Prediction (SEHP) framework, which utilizes diffusion models to tackle these challenges.
arXiv Detail & Related papers (2024-11-19T09:16:25Z) - Efficient Link Prediction via GNN Layers Induced by Negative Sampling [86.87385758192566]
Graph neural networks (GNNs) for link prediction can loosely be divided into two broad categories.
We propose a novel GNN architecture whereby the emphforward pass explicitly depends on emphboth positive (as is typical) and negative (unique to our approach) edges.
This is achieved by recasting the embeddings themselves as minimizers of a forward-pass-specific energy function that favors separation of positive and negative samples.
arXiv Detail & Related papers (2023-10-14T07:02:54Z) - Enhancing Hyperedge Prediction with Context-Aware Self-Supervised Learning [57.35554450622037]
We propose a novel hyperedge prediction framework (CASH)
CASH employs context-aware node aggregation to capture complex relations among nodes in each hyperedge for (C1) and (2) self-supervised contrastive learning in the context of hyperedge prediction to enhance hypergraph representations for (C2)
Experiments on six real-world hypergraphs reveal that CASH consistently outperforms all competing methods in terms of the accuracy in hyperedge prediction.
arXiv Detail & Related papers (2023-09-11T20:06:00Z) - Bias Mimicking: A Simple Sampling Approach for Bias Mitigation [57.17709477668213]
We introduce a new class-conditioned sampling method: Bias Mimicking.
Bias Mimicking improves underrepresented groups' accuracy of sampling methods by 3% over four benchmarks.
arXiv Detail & Related papers (2022-09-30T17:33:00Z) - Language Model-driven Negative Sampling [8.299192665823542]
Knowledge Graph Embeddings (KGEs) encode the entities and relations of a knowledge graph (KG) into a vector space with a purpose of representation learning and reasoning for an ultimate downstream task (i.e., link prediction, question answering)
Since KGEs follow closed-world assumption and assume all the present facts in KGs to be positive (correct), they also require negative samples as a counterpart for learning process for truthfulness test of existing triples.
We propose an approach for generating negative sampling considering the existing rich textual knowledge in KGs.
arXiv Detail & Related papers (2022-03-09T13:27:47Z) - Scalable Personalised Item Ranking through Parametric Density Estimation [53.44830012414444]
Learning from implicit feedback is challenging because of the difficult nature of the one-class problem.
Most conventional methods use a pairwise ranking approach and negative samplers to cope with the one-class problem.
We propose a learning-to-rank approach, which achieves convergence speed comparable to the pointwise counterpart.
arXiv Detail & Related papers (2021-05-11T03:38:16Z) - When Hearst Is not Enough: Improving Hypernymy Detection from Corpus
with Distributional Models [59.46552488974247]
This paper addresses whether an is-a relationship exists between words (x, y) with the help of large textual corpora.
Recent studies suggest that pattern-based ones are superior, if large-scale Hearst pairs are extracted and fed, with the sparsity of unseen (x, y) pairs relieved.
For the first time, this paper quantifies the non-negligible existence of those specific cases. We also demonstrate that distributional methods are ideal to make up for pattern-based ones in such cases.
arXiv Detail & Related papers (2020-10-10T08:34:19Z) - SCE: Scalable Network Embedding from Sparsest Cut [20.08464038805681]
Large-scale network embedding is to learn a latent representation for each node in an unsupervised manner.
A key of success to such contrastive learning methods is how to draw positive and negative samples.
In this paper, we propose SCE for unsupervised network embedding only using negative samples for training.
arXiv Detail & Related papers (2020-06-30T03:18:15Z) - Hypermodels for Exploration [27.66567077899924]
We study the use of hypermodels to represent uncertainty and guide exploration.
This generalizes and extends the use of ensembles to approximate Thompson sampling.
We show that alternative hypermodels can enjoy dramatic efficiency gains.
arXiv Detail & Related papers (2020-06-12T20:59:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.