arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.17073cs.LGcs.AIcs.SI
收藏

用于节点分类和链接预测的超维表示学习

Hyperdimensional Representation Learning for Node Classification and Link Prediction

The Pennsylvania State University(宾夕法尼亚州立大学)

Abhishek Dalvi, Vasant Honavar

AI总结:

本文提出超维图学习器(HDGL),利用超维空间表示和注入性属性,单次遍历实现节点分类与链接预测,以低计算成本达到与先进GNN竞争的性能。

摘要:

我们引入了超维图学习器(HDGL),一种用于图中节点分类和链接预测的新方法。HDGL利用一类图神经网络(GNN)中节点表示的注入性属性,将节点特征映射到非常高维的空间(简称超维空间或HD空间),然后使用超维算子如捆绑和绑定来聚合每个节点局部邻域的信息,产生能够支持节点分类和链接预测任务的潜在节点表示。与依赖计算昂贵的迭代优化和超参数调优的GNN不同,HDGL仅需对数据集进行单次遍历。我们报告了使用广泛使用的基准数据集的实验结果,表明在节点分类任务上,HDGL在显著降低计算成本的同时,达到了与最先进的GNN方法相竞争的准确度;在链接预测任务上,HDGL与DeepWalk及相关方法的性能相当,尽管它不及计算需求高的最先进GNN。

英文摘要:

We introduce Hyperdimensional Graph Learner (HDGL), a novel method for node classification and link prediction in graphs. HDGL maps node features into a very high-dimensional space (\textit{hyperdimensional} or HD space for short) using the \emph{injectivity} property of node representations in a family of Graph Neural Networks (GNNs) and then uses HD operators such as \textit{bundling} and \textit{binding} to aggregate information from the local neighborhood of each node yielding latent node representations that can support both node classification and link prediction tasks. HDGL, unlike GNNs that rely on computationally expensive iterative optimization and hyperparameter tuning, requires only a single pass through the data set. We report results of experiments using widely used benchmark datasets which demonstrate that, on the node classification task, HDGL achieves accuracy that is competitive with that of the state-of-the-art GNN methods at substantially reduced computational cost; and on the link prediction task, HDGL matches the performance of DeepWalk and related methods, although it falls short of computationally demanding state-of-the-art GNNs.

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。

↑