arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05962cs.LG
收藏

EXGC:在图压缩中桥接效率与可解释性

EXGC: Bridging Efficiency and Explainability in Graph Condensation

University of Science and Technology of China(中国科学技术大学);Hunan University(湖南大学);Tongji University(同济大学);National University of Singapore(新加坡国立大学);Institute of Dataspace(数据空间研究院)

Junfeng Fang, Xinglin Li, Yongduo Sui, Yuan Gao, Guibin Zhang, Kun Wang, Xiang Wang, Xiangnan He

AI总结:

EXGC通过平均场变分近似和梯度信息瓶颈目标,解决图压缩中的效率与参数冗余问题,同时引入可解释性,在八个数据集上验证了其优越性。

摘要:

在诸如网络数据等大规模数据集上的图表示学习已经取得了显著进展。然而,相关的计算和存储开销引发了担忧。有鉴于此,图压缩(GCond)被引入,旨在将这些大型真实数据集蒸馏为更简洁但信息丰富的合成图。尽管已有加速努力,现有的GCond方法主要面临效率问题,尤其是在扩展的网络数据图上。因此,在本工作中,我们指出了当前范式的两个主要低效之处:(1)同时更新大量参数集,以及(2)显著的参数冗余。为了分别应对这两个限制,我们首先(1)采用平均场变分近似来加速收敛,然后(2)提出梯度信息瓶颈(GDIB)目标来剪除冗余。通过整合领先的解释技术(如GNNExplainer和GSAT)来实现GDIB,我们提出了EXGC,即高效且可解释的图压缩方法,该方法能显著提升效率并注入可解释性。我们在八个数据集上的广泛评估突显了EXGC的优越性和相关性。代码可在 https://github.com/MangoKiller/EXGC 获取。

英文摘要:

Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of this, Graph condensation (GCond) has been introduced to distill these large real datasets into a more concise yet information-rich synthetic graph. Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs. Hence, in this work, we pinpoint two major inefficiencies of current paradigms: (1) the concurrent updating of a vast parameter set, and (2) pronounced parameter redundancy. To counteract these two limitations correspondingly, we first (1) employ the Mean-Field variational approximation for convergence acceleration, and then (2) propose the objective of Gradient Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB, our EXGC, the Efficient and eXplainable Graph Condensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC's superiority and relevance. Code is available at https://github.com/MangoKiller/EXGC.

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。

↑