arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.08207cs.LG
收藏

BG-HGNN:面向复杂异构图的高效学习

BG-HGNN: Toward Efficient Learning for Complex Heterogeneous Graphs

Ant Group China(蚂蚁集团)

Junwei Su, Lingjun Mao, Zheng Da, Chuan Wu

AI总结:

BG-HGNN通过整合和蒸馏关系异质性到共享的低维特征空间,提升复杂异构图学习的效率和表现。

摘要:

异构图由多种节点和边类型通过不同关系连接而成,在现实世界应用中非常普遍。消息传递异构图神经网络(HGNN)已成为处理此类数据的强大模型类别。然而,现有的HGNN通常为每种关系类型分配一组可学习的权重以建模关系异质性。尽管有潜力,这些模型主要适用于简单的异构图,仅包含少数关系类型。在本文中,我们表明这种标准设计本质上会导致参数爆炸(可学习参数的数量随着关系类型的数量迅速增加)和关系崩溃(模型失去区分不同关系的能力)。这些问题使现有的HGNN在复杂异构图中效率低下或不实用。为了解决这些挑战,我们提出了Blend&Grind-HGNN(BG-HGNN),一种统一的特征表示框架,将关系异质性整合并蒸馏到共享的低维特征空间中。这种设计消除了对关系特定参数集的需求,并使在关系数量增加时仍能高效、表达性地学习。实证研究表明,BG-HGNN在最先进的HGNN上取得了显著的提升,参数效率提高了高达28.96倍,训练吞吐量提高了高达110.30倍,同时在复杂的异构图上匹配或超越了其准确性。

英文摘要:

Heterogeneous graphs, comprising diverse node and edge types connected through varied relations, are ubiquitous in real-world applications. Message-passing heterogeneous graph neural networks (HGNNs) have emerged as a powerful model class for such data. However, existing HGNNs typically allocate a separate set of learnable weights for each relation type to model relational heterogeneity. Despite their promise, these models are effective primarily on simple heterogeneous graphs with only a few relation types. In this paper, we show that this standard design inherently leads to parameter explosion (the number of learnable parameters grows rapidly with the number of relation types) and relation collapse (the model loses the ability to distinguish among different relations). These issues make existing HGNNs inefficient or impractical for complex heterogeneous graphs with many relation types. To address these challenges, we propose Blend&Grind-HGNN (BG-HGNN), a unified feature-representation framework that integrates and distills relational heterogeneity into a shared low-dimensional feature space. This design eliminates the need for relation-specific parameter sets and enables efficient, expressive learning even as the number of relations grows. Empirically, BG-HGNN achieves substantial gains over state-of-the-art HGNNs, improving parameter efficiency by up to 28.96x and training throughput by up to 110.30x, while matching or surpassing their accuracy on complex heterogeneous graphs.

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。

↑