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 2303.02393cs.LGcs.AI
收藏

Seq-HyGAN:基于超图注意力网络的序列分类

Seq-HyGAN: Sequence Classification via Hypergraph Attention Network

Georgia State University(佐治亚州立大学);Arkansas Tech University(阿肯色理工大学);Oklahoma State University(俄克拉荷马州立大学)

Khaled Mohammed Saifuddin, Corey May, Farhan Tanvir, Muhammad Ifte Khairul Islam, Esra Akbas

AI总结:

针对序列分类中现有模型难捕捉全局高阶信息的问题,提出基于超图注意力网络的Seq-HyGAN模型,通过超图表征序列与子序列关系及两级注意力机制学习关键子序列,在四个数据集上性能优于现有最优方法。

摘要:

序列分类在医疗领域的基因组分类、商业领域的异常检测等不同领域有着广泛的现实应用。然而,序列数据中缺乏显式特征,这给机器学习模型带来了困难。尽管神经网络(NN)模型通过自动学习特征解决了这一问题,但它们仅能捕捉相邻的结构连接,忽略了序列之间的全局高阶信息。为应对序列分类问题中的这些挑战,我们提出了一种新型超图注意力网络模型,即Seq-HyGAN。为捕捉序列数据间复杂的结构相似性,我们首先构建了一个超图,其中序列被表示为超边,从序列中提取的子序列被表示为节点。此外,我们提出了一种基于注意力的超图神经网络模型,该模型采用两级注意力机制,在生成作为超边的序列表示的同时,学习每条序列的关键子序列。我们在四个数据集上开展了大量实验,以评估并对比我们的模型与若干当前最优方法。实验结果表明,我们提出的Seq-HyGAN模型能够有效对序列数据进行分类,且性能显著优于基线模型。我们还开展了案例研究,以探究Seq-HyGAN中各模块的作用。

英文摘要:

Sequence classification has a wide range of real-world applications in different domains, such as genome classification in health and anomaly detection in business. However, the lack of explicit features in sequence data makes it difficult for machine learning models. While Neural Network (NN) models address this with learning features automatically, they are limited to capturing adjacent structural connections and ignore global, higher-order information between the sequences. To address these challenges in the sequence classification problems, we propose a novel Hypergraph Attention Network model, namely Seq-HyGAN. To capture the complex structural similarity between sequence data, we first create a hypergraph where the sequences are depicted as hyperedges and subsequences extracted from sequences are depicted as nodes. Additionally, we introduce an attention-based Hypergraph Neural Network model that utilizes a two-level attention mechanism. This model generates a sequence representation as a hyperedge while simultaneously learning the crucial subsequences for each sequence. We conduct extensive experiments on four data sets to assess and compare our model with several state-of-the-art methods. Experimental results demonstrate that our proposed Seq-HyGAN model can effectively classify sequence data and significantly outperform the baselines. We also conduct case studies to investigate the contribution of each module in Seq-HyGAN.

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。

↑