arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.03396cs.LGcs.AI
收藏

GraphCroc:用于图结构重构的互相关自编码器

GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction

Northeastern University(东北大学)

Shijin Duan, Ruyi Ding, Jiaxing He, Aidong Adam Ding, Yunsi Fei, Xiaolin Xu

AI总结:

本文针对现有图自编码器依赖自相关难以准确表示孤岛、对称结构和有向边等图特征的问题,提出互相关机制和GraphCroc模型,通过镜像编解码与损失平衡策略实现更稳健的图结构重构,并在理论和实验上验证其优于现有方法。

摘要:

图结构数据是许多应用的重要组成部分,推动了各种图表示方法的发展。其中,图自编码器(GAE)能够从节点嵌入中重构图结构。当前的GAE模型主要利用自相关来表示图结构,并侧重于节点级任务,往往忽视了多图场景。我们的理论分析表明,自相关在准确表示特定图特征(如孤岛、对称结构和有向边)方面通常存在不足,尤其是在较小或多个图的上下文中。为了解决这些局限性,我们引入了一种互相关机制,显著增强了GAE的表示能力。此外,我们提出了GraphCroc,这是一种新的GAE,支持灵活的编码器架构,可针对各种下游任务进行定制,并通过镜像编码-解码过程确保稳健的结构重构。该模型还通过实施损失平衡策略,解决了优化过程中的表示偏差挑战。理论分析和数值评估均表明,我们的方法在图结构重构方面显著优于现有的基于自相关的GAE。

英文摘要:

Graph-structured data is integral to many applications, prompting the development of various graph representation methods. Graph autoencoders (GAEs), in particular, reconstruct graph structures from node embeddings. Current GAE models primarily utilize self-correlation to represent graph structures and focus on node-level tasks, often overlooking multi-graph scenarios. Our theoretical analysis indicates that self-correlation generally falls short in accurately representing specific graph features such as islands, symmetrical structures, and directional edges, particularly in smaller or multiple graph contexts. To address these limitations, we introduce a cross-correlation mechanism that significantly enhances the GAE representational capabilities. Additionally, we propose GraphCroc, a new GAE that supports flexible encoder architectures tailored for various downstream tasks and ensures robust structural reconstruction, through a mirrored encoding-decoding process. This model also tackles the challenge of representation bias during optimization by implementing a loss-balancing strategy. Both theoretical analysis and numerical evaluations demonstrate that our methodology significantly outperforms existing self-correlation-based GAEs in graph structure reconstruction.

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。

↑