$\alpha$-Graph：基于注意力注入的归一化流方法实现可处理的图建模

中文摘要 AI 辅助

图建模是表示图结构数据中复杂关系的关键任务，近年来取得了显著成功。然而，当前的图建模方法依赖传统的图神经网络和预训练方法，隐式地学习图数据的底层关系结构。因此，这些先前的方法无法捕捉输入之间的复杂图结构和相关性。在本文中，我们提出了一种新颖的基于注意力的归一化流方法（ANFA或$\alpha$），该方法提供了显式、可解释且可处理的图建模（$\alpha$-Graph）。具体而言，我们提出了一种带有可逆注意力机制的无条件图归一化流，以捕捉图数据的复杂关系结构。为了进一步增强模型的表达能力，我们引入了带有可学习查询的条件图归一化流，从而能够高效建模图结构数据中的相关性。我们表明，我们的条件图归一化流在行为上与无条件图归一化流相似，在增强表达能力的同时保持了训练稳定性和效率。我们在三个基准上的实验结果表明，所提出的$\alpha$-Graph方法具有有效性和最先进的（SoTA）性能。

英文摘要

Graph modeling, a crucial task for representing complex relationships in graph-structured data, has achieved significant success in recent years. However, current graph modeling methods rely on traditional Graph Neural Networks and pre-training approaches to implicitly learn the underlying relational structure of graph data. Thus, these prior methods cannot capture the complex graph structure and correlations among inputs. In this paper, we introduce a novel Attention-based Normalizing Flow-based Approach\footnote{Our implementation and models will be released publicly for research reproducibility.} (ANFA or $α$) that provides an explicit, interpretable, and tractable Graph Modeling ($α$-Graph). In particular, we propose a new Unconditional Graph Normalizing Flow with an Invertible Attention Mechanism to capture the complex relational structure of graph data. To further enhance the expressiveness of the model, we introduce Conditional Graph Normalizing Flow with Learnable Queries that enables efficient modeling of correlations in graph-structured data. We show that our Conditional Graph Normalizing Flows behave similarly to Unconditional Graph Normalizing Flows, enhancing expressiveness while maintaining training stability and efficiency. Our experimental results on three benchmarks will illustrate the effectiveness and the state-of-the-art (SoTA) performance of the proposed $α$-Graph method.

发表机构

• University of Arkansas（阿肯色大学）
• Carnegie Mellon University（卡内基梅隆大学）
• Washington State University Vancouver（华盛顿州立大学温哥华分校）

机构由 AI 辅助整理，请以论文原文为准。