$\alpha$-Graph: Attention-Infused Normalizing Flow Approach to Tractable Graph Modeling

2026-09-07

AI Summary

该研究提出了一种基于注意力机制的规范化流方法（ANFA或α-Graph），以显式、可解释的方式解决图结构数据中复杂关系和相关性的建模问题。

Abstract

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 $\alpha$) that provides an explicit, interpretable, and tractable Graph Modeling ($\alpha$-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 $\alpha$-Graph method.

Problem

• Graph Modeling
• Normalizing Flow
• Attention Mechanism
• Relational Structure

Innovation

• Attention-based Normalizing Flow
• Invertible Attention Mechanism
• Conditional Graph Normalizing Flow
• Learnable Queries