Collaborative contrastive learning for hypergraph node classification

Wu, Hanrui; Li, Nuosi; Zhang, Jia; Chen, Sentao; Ng, Michael K.; Long, Jinyi

doi:10.1016/j.patcog.2023.109995

Cited by 13 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…确地捕捉实际系统的结构特征, 并且基于超图的算法已被应用于社区发现 [59] 、节点分类 [60] 和网络演化分析 [61] 等任务. 此外, 超图的研究还涉及到高阶图神经网络的发展, 这是融合了超图理论和深度学习的前沿方向, 其目标是提高数据的表示能力和预测精度 [62] .…”

Section: 一些研究突破包括新型超图模型的开发旨在更准unclassified

Fundamental statistics of higher-order networks: a survey

Liu,

Zeng,

Yang

et al. 2024

Acta Phys. Sin.

View full text Add to dashboard Cite

Complex networks serve as indispensable instruments for characterizing and comprehending intricate real-world systems. Recently, researchers have delved into the realm of higher-order networks, seeking to delineate interactions within these networks with greater precision or analyzing traditional pairwise networks from a higher-dimensional perspective. This endeavor has unearthed novel phenomena distinct from those observed in conventional pairwise networks. However, despite the significance of higher-order networks, research in this area remains comparatively sparse. Furthermore, the intricacy of higher-order interactions has led to a dearth of standardized definitions for their structural statistical measures, posing additional challenges in their investigation. In recognition of these challenges, this paper presents a comprehensive survey of commonly employed statistics and their underlying physical significance in two prevalent types of higher-order networks:hypergraphs and simplicial complex networks. It not only outlines the specific calculation methods and application scenarios of these statistical indicators but also provides a glimpse into future research trends. This comprehensive overview serves as a valuable resource for beginners or cross-disciplinary researchers interested in higher-order networks, enabling them to swiftly grasp the fundamental statistics pertaining to these advanced structures. By fostering a deeper understanding of higher-order networks, this paper facilitates quantitative analysis of their structural characteristics and serves as a guide for researchers aiming to develop novel statistical methods tailored to higher-order networks.

show abstract

Section: 一些研究突破包括新型超图模型的开发旨在更准unclassified

Fundamental statistics of higher-order networks: a survey

Liu,

Zeng,

Yang

et al. 2024

Acta Phys. Sin.

View full text Add to dashboard Cite

show abstract

“…In [24], Li et al have demonstrated that EEG data can have high-order relations in time series. Therefore, IRF indicates the high-order relations among data in a domain 4 by a hypergraph [25,26]. Following [26], we develop hypergraph encoders for the source and target domains to learn the high-order representations by integrating information from both nodes and hyperedges in each layer.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised heterogeneous domain adaptation for EEG classification

Wu,

Xie,

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

$Objective.$ Domain adaptation has been recognized as a potent solution to the challenge of limited training data for electroencephalography (EEG) classification tasks. Existing studies primarily focus on homogeneous environments, however, the heterogeneous properties of EEG data arising from device diversity cannot be overlooked. This motivates the development of heterogeneous domain adaptation methods that can fully exploit the knowledge from an auxiliary heterogeneous domain for EEG classification. $Approach.$ In this article, we propose a novel model named Informative Representation Fusion (IRF) to tackle the problem of unsupervised heterogeneous domain adaptation in the context of EEG data. In IRF, we consider different perspectives of data, i.e., independent identically distributed (iid) and non-iid, to learn different representations. Specifically, from the non-iid perspective, IRF models high-order correlations among data by hypergraphs and develops hypergraph encoders to obtain data representations of each domain. From the non-iid perspective, by applying multi-layer perceptron networks to the source and target domain data, we achieve another type of representation for both domains. Subsequently, an attention mechanism is used to fuse these two types of representations to yield informative features. To learn transferable representations, the Maximum Mean Discrepancy is utilized to align the distributions of the source and target domains based on the fused features. $Main~results.$ Experimental results on several real-world datasets demonstrate the effectiveness of the proposed model. $Significance.$ This article handles an EEG classification situation where the source and target EEG data lie in different spaces, and what's more, under an unsupervised learning setting. This situation is practical in the real world but barely studied in the literature. The proposed model achieves high classification accuracy, and this study is important for the commercial applications of EEG-based BCIs.

show abstract

High-order proximity and relation analysis for cross-network heterogeneous node classification

Wu,

et al. 2024

Mach Learn

View full text Add to dashboard Cite

Collaborative contrastive learning for hypergraph node classification

Cited by 13 publications

References 29 publications

Fundamental statistics of higher-order networks: a survey

Fundamental statistics of higher-order networks: a survey

Unsupervised heterogeneous domain adaptation for EEG classification

High-order proximity and relation analysis for cross-network heterogeneous node classification

Contact Info

Product

Resources

About