arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.04883cs.LGcs.SI
收藏

理解图表示学习中的社区偏差放大

Understanding Community Bias Amplification in Graph Representation Learning

Fudan University(复旦大学);Ant Group(蚂蚁集团)

Shengzhong Zhang, Wenjie Yang, Yimin Zhang, Hongwei Zhang, Divin Yan, Zengfeng Huang

AI总结:

本文从谱视角揭示图表示学习中的社区偏差放大机制,提出随机图粗化及 RGCCL 对比学习模型以缓解该偏差。

摘要:

在本工作中,我们发现了图表示学习中的一种社区偏差放大现象,它指的是图表示学习加剧不同类别之间性能偏差的情况。我们从一个新颖的谱视角对该现象进行了深入的理论研究。我们的分析表明,社区之间的结构偏差会导致节点嵌入具有不同的局部收敛速度。这一现象会导致下游任务分类结果中的偏差放大。基于这些理论洞见,我们提出了随机图粗化,该方法被证明可有效处理上述问题。最后,我们提出了一种名为 Random Graph Coarsening Contrastive Learning(RGCCL,随机图粗化对比学习)的新型图对比学习模型,该模型利用随机粗化作为数据增强,并通过将粗化图与原始图进行对比来缓解社区偏差。在多个数据集上的大量实验证明了我们的方法在处理社区偏差放大时的优势。

英文摘要:

In this work, we discover a phenomenon of community bias amplification in graph representation learning, which refers to the exacerbation of performance bias between different classes by graph representation learning. We conduct an in-depth theoretical study of this phenomenon from a novel spectral perspective. Our analysis suggests that structural bias between communities results in varying local convergence speeds for node embeddings. This phenomenon leads to bias amplification in the classification results of downstream tasks. Based on the theoretical insights, we propose random graph coarsening, which is proved to be effective in dealing with the above issue. Finally, we propose a novel graph contrastive learning model called Random Graph Coarsening Contrastive Learning (RGCCL), which utilizes random coarsening as data augmentation and mitigates community bias by contrasting the coarsened graph with the original graph. Extensive experiments on various datasets demonstrate the advantage of our method when dealing with community bias amplification.

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。

↑