无需预设概念即可生成自然语言解释的可解释模型
Explanation Bottleneck Models
- 通过视觉-语言编码器解码器自动生成解释文本
- 在无需预定义概念集下仍保持高任务准确率与流畅解释
- 适合需要灵活解释且关注可解释性的人工智能应用
近期基于概念的可解释模型通过预定义概念集提供了有意义的解释，但受限于概念数量，应用范围有限。本文提出一种新型可解释深度神经网络——解释瓶颈模型（XBMs）。XBMs从输入中自动生成自然语言解释，无需预定义概念，并利用预训练的视觉-语言编码器-解码器进行最终任务预测。为兼顾任务性能与解释质量，采用目标任务损失，并通过冻结的预训练解码器对解释解码器进行知识蒸馏以施加正则化。实验表明，与当前最优概念瓶颈模型相比，XBMs在无需预定义概念集的情况下仍能提供准确且流畅的自然语言解释。代码已公开于 https://github.com/yshinya6/xbm/。
原文摘要 · Abstract (English)
Recent concept-based interpretable models have succeeded in providing meaningful explanations by pre-defined concept sets. However, the dependency on the pre-defined concepts restricts the application because of the limited number of concepts for explanations. This paper proposes a novel interpretable deep neural network called explanation bottleneck models (XBMs). XBMs generate a text explanation from the input without pre-defined concepts and then predict a final task prediction based on the generated explanation by leveraging pre-trained vision-language encoder-decoder models. To achieve both the target task performance and the explanation quality, we train XBMs through the target task loss with the regularization penalizing the explanation decoder via the distillation from the frozen pre-trained decoder. Our experiments, including a comparison to state-of-the-art concept bottleneck models, confirm that XBMs provide accurate and fluent natural language explanations without pre-defined concept sets. Code is available at https://github.com/yshinya6/xbm/.
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。