arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.09778cs.LGeess.SP
收藏

Hypergraph-MLP:无消息传递的超图学习

Hypergraph-MLP: Learning on Hypergraphs without Message Passing

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

Bohan Tang, Siheng Chen, Xiaowen Dong

AI总结:

针对超图神经网络中消息传递导致的过平滑、高延迟和脆弱性问题,提出Hypergraph-MLP框架,将结构信息融入训练监督,以简单MLP实现竞争性能并提升推理速度与鲁棒性。

摘要:

超图在建模包含两个以上实体的高阶关系数据中至关重要,在机器学习和信号处理领域日益受到重视。许多超图神经网络利用超图结构上的消息传递来增强节点表示学习,在超图节点分类等任务中取得了令人瞩目的性能。然而,这些基于消息传递的模型面临若干挑战,包括过平滑以及推理时的高延迟和对结构扰动的敏感性。为应对这些挑战,我们提出了一种替代方法,将超图结构的信息整合到训练监督中,而不进行显式消息传递,从而也消除了推理时对其的依赖。具体而言,我们引入了Hypergraph-MLP,一种用于超图结构数据的新型学习框架,其中学习模型是一个简单的多层感知器(MLP),由基于超图上信号平滑性概念的损失函数监督。在超图节点分类任务上的实验表明,Hypergraph-MLP与现有基线相比取得了具有竞争力的性能,并且在推理时速度显著更快且对结构扰动更具鲁棒性。

英文摘要:

Hypergraphs are vital in modelling data with higher-order relations containing more than two entities, gaining prominence in machine learning and signal processing. Many hypergraph neural networks leverage message passing over hypergraph structures to enhance node representation learning, yielding impressive performances in tasks like hypergraph node classification. However, these message-passing-based models face several challenges, including oversmoothing as well as high latency and sensitivity to structural perturbations at inference time. To tackle those challenges, we propose an alternative approach where we integrate the information about hypergraph structures into training supervision without explicit message passing, thus also removing the reliance on it at inference. Specifically, we introduce Hypergraph-MLP, a novel learning framework for hypergraph-structured data, where the learning model is a straightforward multilayer perceptron (MLP) supervised by a loss function based on a notion of signal smoothness on hypergraphs. Experiments on hypergraph node classification tasks demonstrate that Hypergraph-MLP achieves competitive performance compared to existing baselines, and is considerably faster and more robust against structural perturbations at inference.

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。

↑