用扩散自编码器和聚类生成多样反事实解释
DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering
- 在隐空间聚类发现类别内不同模式方向
- 生成多个差异明显且有意义的反事实样本
- 适合需要可解释性的AI决策场景
为同一类别中的不同数据模式生成多个反事实解释是一项重大挑战，因为这些模式虽各异却共享相同分类结果。扩散概率模型（DPMs）展现出捕捉数据分布底层模式的强大能力。本文提出DifCluE方法，利用扩散自编码器在隐空间进行聚类，识别出类别内部不同模式对应的生成方向，从而生成多样化且语义合理的反事实解释。实验表明，DifCluE在生成多反事实解释方面优于当前最先进方法，显著提升了模型可解释性。
原文摘要 · Abstract (English)
Generating multiple counterfactual explanations for different modes within a class presents a significant challenge, as these modes are distinct yet converge under the same classification. Diffusion probabilistic models (DPMs) have demonstrated a strong ability to capture the underlying modes of data distributions. In this paper, we harness the power of a Diffusion Autoencoder to generate multiple distinct counterfactual explanations. By clustering in the latent space, we uncover the directions corresponding to the different modes within a class, enabling the generation of diverse and meaningful counterfactuals. We introduce a novel methodology, DifCluE, which consistently identifies these modes and produces more reliable counterfactual explanations. Our experimental results demonstrate that DifCluE outperforms the current state-of-the-art in generating multiple counterfactual explanations, offering a significant advancement in model interpretability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。