提出高效计算高维模型对比解释的新算法，提升可解释性效率。
Efficient Contrastive Explanations on Demand
- 利用对抗鲁棒性加速大规模特征模型的对比解释生成
- 在多个数据集上实现显著更快的解释计算速度
- 适合需要快速可解释性的深度学习应用开发者
近期研究揭示了对抗鲁棒性与距离型（形式化）符号解释之间的紧密联系。这一发现意义重大，因为它标志着将符号解释的计算效率提升至与判断对抗样本存在性相当水平的初步尝试，尤其适用于复杂机器学习模型。然而，主要性能瓶颈仍存，源于机器学习模型可能包含大量特征，尤其是深度神经网络。本文提出新型算法，通过利用对抗鲁棒性，实现对具有大量特征的机器学习模型的对比解释计算。此外，还提出了列举解释和寻找最小对比解释的新算法。实验结果表明，本文提出的算法在性能上取得了显著提升。
原文摘要 · Abstract (English)
Recent work revealed a tight connection between adversarial robustness and restricted forms of symbolic explanations, namely distance-based (formal) explanations. This connection is significant because it represents a first step towards making the computation of symbolic explanations as efficient as deciding the existence of adversarial examples, especially for highly complex machine learning (ML) models. However, a major performance bottleneck remains, because of the very large number of features that ML models may possess, in particular for deep neural networks. This paper proposes novel algorithms to compute the so-called contrastive explanations for ML models with a large number of features, by leveraging on adversarial robustness. Furthermore, the paper also proposes novel algorithms for listing explanations and finding smallest contrastive explanations. The experimental results demonstrate the performance gains achieved by the novel algorithms proposed in this paper.
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。