用逻辑编程解释神经网络的用户偏好预测，让黑箱模型更透明。
Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach
- 用弱约束的归纳逻辑编程逼近神经网络的偏好预测逻辑。
- 在高维特征空间下保持解释精度，计算时间增长可控。
- 适合需要可解释性的人工智能应用，如个性化推荐系统。
本文提出利用从答案集学习（Learning from Answer Sets）来近似黑箱模型（如神经网络），特别是在用户偏好学习场景中。我们重点探索使用ILASP（归纳答案集程序学习）通过弱约束逼近偏好学习系统。为此，我们构建了一个关于食谱偏好的数据集，用于训练神经网络，并以之为目标进行逻辑程序近似。实验考察了ILASP作为全局与局部近似的性能，旨在应对高维特征空间中模型逼近的挑战：既要保证目标模型的保真度，又需控制计算时间增长。为此，我们提出预处理步骤，采用主成分分析（PCA）降低数据维度，同时保持解释的可读性。研究结果表明，该方法在保持解释透明性的同时，有效提升了高维场景下的逼近效率。论文投稿至《理论与实践中的逻辑编程》（TPLP）。
原文摘要 · Abstract (English)
In this paper, we propose using Learning from Answer Sets to approximate black-box models, such as Neural Networks (NN), in the specific case of learning user preferences. We specifically explore the use of ILASP (Inductive Learning of Answer Set Programs) to approximate preference learning systems through weak constraints. We have created a dataset on user preferences over a set of recipes, which is used to train the NNs that we aim to approximate with ILASP. Our experiments investigate ILASP both as a global and a local approximator of the NNs. These experiments address the challenge of approximating NNs working on increasingly high-dimensional feature spaces while achieving appropriate fidelity on the target model and limiting the increase in computational time. To handle this challenge, we propose a preprocessing step that exploits Principal Component Analysis to reduce the dataset's dimensionality while keeping our explanations transparent. Under consideration for publication in Theory and Practice of Logic Programming (TPLP).
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。