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 2312.13616cs.LGcs.AI
收藏

导航结构化反事实空间:通过结构化扩散生成反事实

Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion

IBM Research(IBM研究院);Indian Institute of Delhi(德里印度理工学院)

Nishtha Madaan, Srikanta Bedathur

AI总结:

本文提出结构化反事实扩散器(SCD),首个利用扩散模型为结构化数据生成反事实解释的即插即用框架,通过引导扩散模型生成高合理性、邻近性和多样性的反事实,优于现有方法。

摘要:

生成反事实解释是揭示黑盒神经网络模型内部运作并建立用户信任的最有效方法之一。尽管扩散模型在视觉等领域取得了显著进展,但其在结构化模态中生成反事实解释的效用仍未得到探索。本文介绍了结构化反事实扩散器(SCD),这是首个利用扩散为结构化数据生成反事实解释的即插即用框架。SCD通过扩散模型学习底层数据分布,并在测试时引导该模型为任意黑盒模型、输入和期望预测生成反事实。我们的实验表明,与现有最先进方法相比,我们的反事实不仅具有更高的合理性,而且在邻近性和多样性方面也表现出显著优势。

英文摘要:

Generating counterfactual explanations is one of the most effective approaches for uncovering the inner workings of black-box neural network models and building user trust. While remarkable strides have been made in generative modeling using diffusion models in domains like vision, their utility in generating counterfactual explanations in structured modalities remains unexplored. In this paper, we introduce Structured Counterfactual Diffuser or SCD, the first plug-and-play framework leveraging diffusion for generating counterfactual explanations in structured data. SCD learns the underlying data distribution via a diffusion model which is then guided at test time to generate counterfactuals for any arbitrary black-box model, input, and desired prediction. Our experiments show that our counterfactuals not only exhibit high plausibility compared to the existing state-of-the-art but also show significantly better proximity and diversity.

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。

↑