论文标题
概念嵌入模型：超越准确性 - 解释性权衡
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
论文作者
论文摘要
部署AI驱动系统需要支持有效人类互动的值得信赖的模型，而不是原始预测准确性。概念瓶颈模型通过在类似人类的概念的中间级别调节分类任务来促进可信度。这使得人类干预措施可以纠正错误预测的概念以改善模型的性能。但是，现有的概念瓶颈模型无法在高任务准确性，基于概念的强大解释和对概念的有效干预措施之间找到最佳的妥协，尤其是在稀缺的完整和准确的概念主管的现实情况下。为了解决这个问题，我们提出了概念嵌入模型，这是一种新型的概念瓶颈模型，它通过学习可解释的高维概念表示形式而超出了当前的准确性-VS解关性权衡。我们的实验表明，概念嵌入模型（1）实现了更好或竞争的任务准确性W.R.T.没有概念的标准神经模型，（2）提供概念表示，捕获有意义的语义，包括其地面真相标签，（3）支持测试时间概念干预措施，其在测试准确性中的影响超过了标准概念瓶颈模型中的效果，以及（4）缩放到现实世界中的现实状况，使完整的概念超级稀缺。
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an intermediate level of human-like concepts. This enables human interventions which can correct mispredicted concepts to improve the model's performance. However, existing concept bottleneck models are unable to find optimal compromises between high task accuracy, robust concept-based explanations, and effective interventions on concepts -- particularly in real-world conditions where complete and accurate concept supervisions are scarce. To address this, we propose Concept Embedding Models, a novel family of concept bottleneck models which goes beyond the current accuracy-vs-interpretability trade-off by learning interpretable high-dimensional concept representations. Our experiments demonstrate that Concept Embedding Models (1) attain better or competitive task accuracy w.r.t. standard neural models without concepts, (2) provide concept representations capturing meaningful semantics including and beyond their ground truth labels, (3) support test-time concept interventions whose effect in test accuracy surpasses that in standard concept bottleneck models, and (4) scale to real-world conditions where complete concept supervisions are scarce.
