可解释的嵌入表示与距离解释器
Explainable embeddings with Distance Explainer
AI总结：
本文提出Distance Explainer，通过选择性遮蔽和距离排序的遮蔽过滤生成嵌入空间的局部后验解释，验证了其在跨模态嵌入中的有效性，提升了深度学习应用的透明度和可信度。
摘要：
尽管可解释AI（XAI）取得了显著进展，但很少有方法解决嵌入向量空间中可解释性的问题，其中维度代表复杂的抽象。我们引入Distance Explainer，一种新的方法，用于生成机器学习模型嵌入空间的局部后验解释。我们的方法借鉴了RISE中的显著性技术，通过选择性遮蔽和距离排序的遮蔽过滤来解释两个嵌入数据点之间的距离。我们使用已建立的XAI指标，包括忠实性、灵敏度/鲁棒性和随机化，对跨模态嵌入（图像-图像和图像-标题对）进行了评估。在ImageNet和CLIP模型上的实验表明，我们的方法能够有效识别导致嵌入数据点相似或不相似的特征，同时保持高鲁棒性和一致性。我们还探讨了参数调整，特别是遮蔽数量和选择策略，对解释质量的影响。这项工作填补了XAI研究中的关键空白，并增强了使用嵌入空间的深度学习应用的透明度和可信度。
英文摘要：
While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance between two embedded data points by assigning attribution values through selective masking and distance-ranked mask filtering. We evaluate Distance Explainer on cross-modal embeddings (image-image and image-caption pairs) using established XAI metrics including Faithfulness, Sensitivity/Robustness, and Randomization. Experiments with ImageNet and CLIP models demonstrate that our method effectively identifies features contributing to similarity or dissimilarity between embedded data points while maintaining high robustness and consistency. We also explore how parameter tuning, particularly mask quantity and selection strategy, affects explanation quality. This work addresses a critical gap in XAI research and enhances transparency and trustworthiness in deep learning applications utilizing embedded spaces.
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。
