发表机构
Indian Institute of Science Education and Research Thiruvananthapuram; Indian Institute of Science Education and Research Kolkata; University of Rostock; Stellenbosch Institute for Advanced Study (STIAS)（印度科学教育与研究学院蒂鲁文南特普拉姆分校; 印度科学教育与研究学院加尔各答分校; 罗斯托克大学; 斯泰伦博斯高等研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
HyperFuse提出一种无标签快速超图嵌入方法，通过谱松弛、多尺度特征和效用加权编码器，在保持精度的同时实现13-179倍加速，适用于多超图或演化场景。
AI 中文摘要
自监督超图表示学习能够产生信息丰富的节点嵌入，但现有方法通常需要训练数百个epoch的深度编码器，即使对于仅有数千个节点的超图，嵌入生成也代价高昂。这限制了需要为多个或演化中的超图生成嵌入的应用。我们提出了HyperFuse，一个用于快速超图表示学习的无标签流水线。HyperFuse (i) 通过最大化超图模块性的谱松弛来计算结构节点坐标，使用Banerjee超图邻接矩阵和线性于节点-超边关联成本的矩阵自由算子；(ii) 构建多尺度特征摘要，并根据特征和成员掩蔽下的成员稳定性为超边分配有界效用权重；(iii) 使用不变性-去相关目标训练一个轻量级效用加权超图编码器，训练100个epoch。我们将HyperFuse与TriCL、SE-HSSL、VilLain和HypeBoy在九个公开超图上使用六个下游分类器和k-means聚类进行比较。在所有方法都完成的八个数据集上，HyperFuse平均每个数据集需要8.7秒，相对于基线实现了13-179倍的几何平均加速。它在六个分类器中的五个上取得了最高平均准确率，而分类和聚类性能与TriCL和SE-HSSL无显著差异。与HypeBoy相比，HyperFuse在所有分类器上快13倍且准确率高2.1-4.1个百分点。HyperFuse为快速、重复的超图嵌入生成提供了一种实用方法。
英文摘要
Self-supervised hypergraph representation learning can produce informative node embeddings, but existing methods often require deep encoders trained for hundreds of epochs, making embedding generation costly even for hypergraphs with a few thousand nodes. This limits applications requiring embeddings for many or evolving hypergraphs. We present HyperFuse, a label-free pipeline for fast hypergraph representation learning. HyperFuse (i) computes structural node coordinates by maximizing a spectral relaxation of hypergraph modularity using Banerjee's hypergraph adjacency and a matrix-free operator with cost linear in node-hyperedge incidences; (ii) constructs multi-scale feature summaries and assigns bounded utility weights to hyperedges based on member stability under feature and membership masking; and (iii) trains a lightweight utility-weighted hypergraph encoder for 100 epochs using an invariance-decorrelation objective. We compare HyperFuse with TriCL, SE-HSSL, VilLain, and HypeBoy on nine public hypergraphs using six downstream classifiers and k-means clustering. On the eight datasets where all methods completed, HyperFuse required 8.7 s per dataset on average, achieving 13-179x geometric-mean speed-ups over the baselines. It achieved the highest average accuracy with five of six classifiers, while classification and clustering performance was not significantly different from TriCL and SE-HSSL. Compared with HypeBoy, HyperFuse was 13x faster and 2.1-4.1 percentage points more accurate across all classifiers. HyperFuse provides a practical approach for fast, repeated hypergraph embedding generation.
