CIDER:基于反事实不变量扩散的 GNN 因果子图推理解释器

Qibin Zhang, Chengshang Lyu, Lingxi Chen, Qiqi Jin, Luonan Chen
{"title":"CIDER:基于反事实不变量扩散的 GNN 因果子图推理解释器","authors":"Qibin Zhang, Chengshang Lyu, Lingxi Chen, Qiqi Jin, Luonan Chen","doi":"arxiv-2407.19376","DOIUrl":null,"url":null,"abstract":"Inferring causal links or subgraphs corresponding to a specific phenotype or\nlabel based solely on measured data is an important yet challenging task, which\nis also different from inferring causal nodes. While Graph Neural Network (GNN)\nExplainers have shown potential in subgraph identification, existing methods\nwith GNN often offer associative rather than causal insights. This lack of\ntransparency and explainability hinders our understanding of their results and\nalso underlying mechanisms. To address this issue, we propose a novel method of\ncausal link/subgraph inference, called CIDER: Counterfactual-Invariant\nDiffusion-based GNN ExplaineR, by implementing both counterfactual and\ndiffusion implementations. In other words, it is a model-agnostic and\ntask-agnostic framework for generating causal explanations based on a\ncounterfactual-invariant and diffusion process, which provides not only causal\nsubgraphs due to counterfactual implementation but reliable causal links due to\nthe diffusion process. Specifically, CIDER is first formulated as an inference\ntask that generatively provides the two distributions of one causal subgraph\nand another spurious subgraph. Then, to enhance the reliability, we further\nmodel the CIDER framework as a diffusion process. Thus, using the causal\nsubgraph distribution, we can explicitly quantify the contribution of each\nsubgraph to a phenotype/label in a counterfactual manner, representing each\nsubgraph's causal strength. From a causality perspective, CIDER is an\ninterventional causal method, different from traditional association studies or\nobservational causal approaches, and can also reduce the effects of unobserved\nconfounders. We evaluate CIDER on both synthetic and real-world datasets, which\nall demonstrate the superiority of CIDER over state-of-the-art methods.","PeriodicalId":501309,"journal":{"name":"arXiv - CS - Computational Engineering, Finance, and Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CIDER: Counterfactual-Invariant Diffusion-based GNN Explainer for Causal Subgraph Inference\",\"authors\":\"Qibin Zhang, Chengshang Lyu, Lingxi Chen, Qiqi Jin, Luonan Chen\",\"doi\":\"arxiv-2407.19376\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Inferring causal links or subgraphs corresponding to a specific phenotype or\\nlabel based solely on measured data is an important yet challenging task, which\\nis also different from inferring causal nodes. While Graph Neural Network (GNN)\\nExplainers have shown potential in subgraph identification, existing methods\\nwith GNN often offer associative rather than causal insights. This lack of\\ntransparency and explainability hinders our understanding of their results and\\nalso underlying mechanisms. To address this issue, we propose a novel method of\\ncausal link/subgraph inference, called CIDER: Counterfactual-Invariant\\nDiffusion-based GNN ExplaineR, by implementing both counterfactual and\\ndiffusion implementations. In other words, it is a model-agnostic and\\ntask-agnostic framework for generating causal explanations based on a\\ncounterfactual-invariant and diffusion process, which provides not only causal\\nsubgraphs due to counterfactual implementation but reliable causal links due to\\nthe diffusion process. Specifically, CIDER is first formulated as an inference\\ntask that generatively provides the two distributions of one causal subgraph\\nand another spurious subgraph. Then, to enhance the reliability, we further\\nmodel the CIDER framework as a diffusion process. Thus, using the causal\\nsubgraph distribution, we can explicitly quantify the contribution of each\\nsubgraph to a phenotype/label in a counterfactual manner, representing each\\nsubgraph's causal strength. From a causality perspective, CIDER is an\\ninterventional causal method, different from traditional association studies or\\nobservational causal approaches, and can also reduce the effects of unobserved\\nconfounders. We evaluate CIDER on both synthetic and real-world datasets, which\\nall demonstrate the superiority of CIDER over state-of-the-art methods.\",\"PeriodicalId\":501309,\"journal\":{\"name\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.19376\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computational Engineering, Finance, and Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.19376","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

仅根据测量数据推断与特定表型或标签相对应的因果联系或子图是一项重要而又具有挑战性的任务,它也不同于推断因果节点。虽然图神经网络(GNN)解释器在子图识别方面显示出了潜力,但现有的图神经网络方法通常提供的是关联而非因果关系的见解。这种缺乏透明度和可解释性的情况阻碍了我们对其结果和内在机制的理解。为了解决这个问题,我们提出了一种新颖的因果链接/子图推断方法,称为 CIDER:基于反事实-不变扩散的 GNN ExplaineR,它同时实现了反事实和扩散两种实现方式。换句话说,它是一个基于反事实不变和扩散过程生成因果解释的模型无关和任务无关框架,不仅能提供反事实实现的因果子图,还能提供扩散过程的可靠因果联系。具体来说,CIDER 首先是一个推理任务,它生成性地提供一个因果子图和另一个虚假子图的两个分布。然后,为了提高可靠性,我们进一步将 CIDER 框架建模为一个扩散过程。这样,利用因果子图分布,我们就能以反事实的方式明确量化每个子图对表型/标签的贡献,代表每个子图的因果强度。从因果关系的角度来看,CIDER 是一种有别于传统关联研究或观察因果关系方法的介入性因果关系方法,它还可以减少未观察到的因果关系的影响。我们在合成数据集和实际数据集上对 CIDER 进行了评估,结果表明 CIDER 优于最先进的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
CIDER: Counterfactual-Invariant Diffusion-based GNN Explainer for Causal Subgraph Inference
Inferring causal links or subgraphs corresponding to a specific phenotype or label based solely on measured data is an important yet challenging task, which is also different from inferring causal nodes. While Graph Neural Network (GNN) Explainers have shown potential in subgraph identification, existing methods with GNN often offer associative rather than causal insights. This lack of transparency and explainability hinders our understanding of their results and also underlying mechanisms. To address this issue, we propose a novel method of causal link/subgraph inference, called CIDER: Counterfactual-Invariant Diffusion-based GNN ExplaineR, by implementing both counterfactual and diffusion implementations. In other words, it is a model-agnostic and task-agnostic framework for generating causal explanations based on a counterfactual-invariant and diffusion process, which provides not only causal subgraphs due to counterfactual implementation but reliable causal links due to the diffusion process. Specifically, CIDER is first formulated as an inference task that generatively provides the two distributions of one causal subgraph and another spurious subgraph. Then, to enhance the reliability, we further model the CIDER framework as a diffusion process. Thus, using the causal subgraph distribution, we can explicitly quantify the contribution of each subgraph to a phenotype/label in a counterfactual manner, representing each subgraph's causal strength. From a causality perspective, CIDER is an interventional causal method, different from traditional association studies or observational causal approaches, and can also reduce the effects of unobserved confounders. We evaluate CIDER on both synthetic and real-world datasets, which all demonstrate the superiority of CIDER over state-of-the-art methods.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A generalized non-hourglass updated Lagrangian formulation for SPH solid dynamics A Knowledge-Inspired Hierarchical Physics-Informed Neural Network for Pipeline Hydraulic Transient Simulation Uncertainty Analysis of Limit Cycle Oscillations in Nonlinear Dynamical Systems with the Fourier Generalized Polynomial Chaos Expansion Micropolar elastoplasticity using a fast Fourier transform-based solver A differentiable structural analysis framework for high-performance design optimization
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1