arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.02018cs.LG
收藏

基于知识转移网络的异构图中Zero-shot迁移学习

Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks

Carnegie Mellon University(卡内基梅隆大学);Google Research(谷歌研究院);University of California Los Angeles(加州大学洛杉矶分校)

Minji Yoon, John Palowitch, Dustin Zelle, Ziniu Hu, Ruslan Salakhutdinov, Bryan Perozzi

摘要:

从社交或电子商务平台等工业生态系统连续发出的数据通常表示为由多个节点/边类型组成的异构图(HG)。被称为异构图神经网络(HGNN)的用于HG的最先进的图学习方法被应用于学习深度上下文通知的节点表示。然而,来自工业应用的许多HG数据集遭受节点类型之间的标签不平衡。由于没有直接的方法来使用植根于不同节点类型的标签进行学习,HGNN仅应用于少数具有丰富标签的节点类型。我们提出了一个zero-shot迁移学习模块的HGNNs称为知识转移网络(KTN),转移知识从标签丰富的节点类型,零标记的节点类型,通过丰富的关系信息在HG。KTN是从理论上的关系,我们在这项工作中介绍,不同的特征提取器之间的HGNN模型中给出的每个节点类型。KTN将6种不同类型的HGNN模型的性能提高了960%,用于零标记节点类型的推理,并在HG上的18个不同的迁移学习任务中将最先进的迁移学习基线性能提高了73%。

英文摘要:

Data continuously emitted from industrial ecosystems such as social or e-commerce platforms are commonly represented as heterogeneous graphs (HG) composed of multiple node/edge types. State-of-the-art graph learning methods for HGs known as heterogeneous graph neural networks (HGNNs) are applied to learn deep context-informed node representations. However, many HG datasets from industrial applications suffer from label imbalance between node types. As there is no direct way to learn using labels rooted at different node types, HGNNs have been applied to only a few node types with abundant labels. We propose a zero-shot transfer learning module for HGNNs called a Knowledge Transfer Network (KTN) that transfers knowledge from label-abundant node types to zero-labeled node types through rich relational information given in the HG. KTN is derived from the theoretical relationship, which we introduce in this work, between distinct feature extractors for each node type given in an HGNN model. KTN improves performance of 6 different types of HGNN models by up to 960% for inference on zero-labeled node types and outperforms state-of-the-art transfer learning baselines by up to 73% across 18 different transfer learning tasks on HGs.

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。

↑