通过类别特异性稀疏化训练，提升神经符号规则提取的准确率与可解释性。
Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters
- 训练时引入类别特异性稀疏损失，动态控制滤波器二值化
- 准确率比当前最优提升9%，规则集规模减少53%
- 适合需要高可解释性且对精度要求高的视觉任务场景
近年来，研究者致力于构建基于卷积神经网络（CNN）的神经符号模型以实现可解释的图像分类。这类方法用CNN作为特征提取器，并从其内部提取可解释的规则集替代原有CNN。然而，现有方法在提取规则集时通常进行后训练滤波器激活二值化，导致性能下降。本文识别出该问题的根本原因在于此阶段的信息丢失。为此，提出一种新颖的稀疏性损失函数，在CNN训练过程中实现类别特异性滤波器二值化，从而最小化规则提取时的信息损失。我们评估了多种结合该损失的训练策略，分析其有效性并提供使用建议。实验表明，所提方法创下新基准：在准确率上较前人SOTA提升9%，规则集平均规模减少53%，同时仅比原始CNN低3%准确率。这证明了可解释神经符号模型在保持高性能的同时具备成为黑箱CNN可行替代方案的巨大潜力。
原文摘要 · Abstract (English)
There has been significant focus on creating neuro-symbolic models for interpretable image classification using Convolutional Neural Networks (CNNs). These methods aim to replace the CNN with a neuro-symbolic model consisting of the CNN, which is used as a feature extractor, and an interpretable rule-set extracted from the CNN itself. While these approaches provide interpretability through the extracted rule-set, they often compromise accuracy compared to the original CNN model. In this paper, we identify the root cause of this accuracy loss as the post-training binarization of filter activations to extract the rule-set. To address this, we propose a novel sparsity loss function that enables class-specific filter binarization during CNN training, thus minimizing information loss when extracting the rule-set. We evaluate several training strategies with our novel sparsity loss, analyzing their effectiveness and providing guidance on their appropriate use. Notably, we set a new benchmark, achieving a 9% improvement in accuracy and a 53% reduction in rule-set size on average, compared to the previous SOTA, while coming within 3% of the original CNN's accuracy. This highlights the significant potential of interpretable neuro-symbolic models as viable alternatives to black-box CNNs.
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。