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 2007.04612cs.LGstat.ML
收藏

概念瓶颈模型

Concept Bottleneck Models

Stanford University(斯坦福大学);Google Research(谷歌研究院)

Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang

摘要:

我们试图学习模型,我们可以使用高级概念进行交互:如果模型不认为x射线中有骨刺,它仍然可以预测严重的关节炎吗?当今最先进的模型通常不支持对诸如“骨刺的存在”之类的概念的操纵,因为它们被端到端地训练以直接从原始输入(例如,像素)输出(例如,关节炎严重程度)。我们重温了经典的想法,首先预测在训练时提供的概念,然后使用这些概念来预测标签。通过构造,我们可以通过编辑它们的预测概念值并将这些变化传播到最终预测来干预这些概念瓶颈模型。在X射线分级和鸟类识别方面,概念瓶颈模型实现了与标准端到端模型竞争的准确性,同时能够根据高级临床概念(“骨刺”)或鸟类属性(“翅膀颜色”)进行解释。这些模型还允许更丰富的人机交互:如果我们能够在测试时纠正模型在概念上的错误,准确性会显著提高。

英文摘要:

We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis? State-of-the-art models today do not typically support the manipulation of concepts like "the existence of bone spurs", as they are trained end-to-end to go directly from raw input (e.g., pixels) to output (e.g., arthritis severity). We revisit the classic idea of first predicting concepts that are provided at training time, and then using these concepts to predict the label. By construction, we can intervene on these concept bottleneck models by editing their predicted concept values and propagating these changes to the final prediction. On x-ray grading and bird identification, concept bottleneck models achieve competitive accuracy with standard end-to-end models, while enabling interpretation in terms of high-level clinical concepts ("bone spurs") or bird attributes ("wing color"). These models also allow for richer human-model interaction: accuracy improves significantly if we can correct model mistakes on concepts at test time.

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。

↑