arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05569cs.LGcs.AIeess.SPstat.ML
收藏

面向超图学习的免训练消息传递

Training-Free Message Passing for Learning on Hypergraphs

University of Oxford(牛津大学);Shanghai Jiao Tong University(上海交通大学);University College London(伦敦大学学院);Shanghai AI Laboratory(上海人工智能实验室)

Bohan Tang, Zexi Liu, Keyue Jiang, Siheng Chen, Xiaowen Dong

AI总结:

本文提出免训练消息传递模块 TF-MP-Module 及 TF-HNN,将超图结构信息的使用与模型训练解耦,在保证性能的同时大幅提升训练效率。

摘要:

超图对于建模现实数据中的高阶交互至关重要。超图神经网络(HNNs)通过消息传递有效利用这些结构,为节点分类等各种下游任务生成具有信息量的节点特征。然而,现有 HNNs 中的消息传递模块通常需要计算密集型的训练过程,这限制了它们的实际应用。为应对这一挑战,我们提出了一种替代方法,将超图结构信息的使用与模型学习阶段解耦。由此产生了一个新颖的免训练消息传递模块,命名为 TF-MP-Module,它可以在数据预处理阶段预先计算,从而降低计算负担。我们将配备 TF-MP-Module 的超图神经网络称为 TF-HNN。我们从理论上支持 TF-HNN 的高效性和有效性,证明:1)与现有 HNNs 相比,它具有更高的训练效率;2)它在节点特征生成中利用了与现有 HNNs 一样多的信息;3)在使用长程交互时,它对过度平滑问题具有鲁棒性。基于七个真实世界超图基准的节点分类和超链接预测实验表明,与最先进的 HNNs 相比,TF-HNN 展现出具有竞争力的性能和优越的训练效率。具体而言,在大规模基准 Trivago 上,TF-HNN 的节点分类准确率比最佳基线高出 10%,而训练时间仅为该基线的 1%。

英文摘要:

Hypergraphs are crucial for modelling higher-order interactions in real-world data. Hypergraph neural networks (HNNs) effectively utilise these structures by message passing to generate informative node features for various downstream tasks like node classification. However, the message passing module in existing HNNs typically requires a computationally intensive training process, which limits their practical use. To tackle this challenge, we propose an alternative approach by decoupling the usage of hypergraph structural information from the model learning stage. This leads to a novel training-free message passing module, named TF-MP-Module, which can be precomputed in the data preprocessing stage, thereby reducing the computational burden. We refer to the hypergraph neural network equipped with our TF-MP-Module as TF-HNN. We theoretically support the efficiency and effectiveness of TF-HNN by showing that: 1) It is more training-efficient compared to existing HNNs; 2) It utilises as much information as existing HNNs for node feature generation; and 3) It is robust against the oversmoothing issue while using long-range interactions. Experiments based on seven real-world hypergraph benchmarks in node classification and hyperlink prediction show that, compared to state-of-the-art HNNs, TF-HNN exhibits both competitive performance and superior training efficiency. Specifically, on the large-scale benchmark, Trivago, TF-HNN outperforms the node classification accuracy of the best baseline by 10% with just 1% of the training time of that baseline.

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。

↑