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 2301.12667cs.LGcs.AIcs.CV
收藏

NeSyFOLD:面向可解释图像分类的神经符号框架

NeSyFOLD: Neurosymbolic Framework for Interpretable Image Classification

University of Texas at Dallas(德克萨斯大学达拉斯分校)

Parth Padalkar, Huaduo Wang, Gopal Gupta

AI总结:

针对深度学习模型缺乏可解释性的问题,提出NeSyFOLD神经符号框架,用分层回答集程序替代CNN全连接层构建可解释分类模型,结合稀疏核学习缩减规则规模,还提出语义标注算法提升规则直观性。

摘要:

卷积神经网络(CNN)等深度学习模型已在图像分类等计算机视觉任务中超越人类表现。然而,尽管这些模型性能先进,却缺乏可解释性,可能导致反映数据中现有偏见的偏差结果。我们旨在让CNN做出的预测具备可解释性,为此提出了名为NeSyFOLD的新型框架,用于构建面向图像分类任务的神经符号(NeSy)模型。该模型是一种CNN,其最后一个卷积层之后的所有层均被分层回答集程序(ASP)替代。我们使用名为FOLD-SE-M的基于规则的机器学习算法,从最后一个卷积层的二值化滤波器激活值中推导分层回答集程序。该回答集程序可视为一个规则集,其中每个谓词的真值取决于CNN中对应卷积核的激活情况。该规则集可作为模型的全局解释,且具备可解释性,神经符号模型预测的依据可通过ASP解释器获取。我们还将NeSyFOLD框架与采用名为Elite BackProp(EBP)的稀疏核学习技术训练的CNN结合使用,这能在不损失准确率或保真度的前提下大幅缩减规则集规模,从而提升神经符号模型的可扩展性及其规则集的可解释性。我们在复杂度和规模各异的数据集上开展了评估。为让规则集更易于直观理解,我们提出了一种新算法,为规则集中每个卷积核对应的谓词标注其学习到的语义概念。我们评估了该“语义标注算法”的性能,以量化语义标注在神经符号模型和神经符号-EBP模型上的效果。

英文摘要:

Deep learning models such as CNNs have surpassed human performance in computer vision tasks such as image classification. However, despite their sophistication, these models lack interpretability which can lead to biased outcomes reflecting existing prejudices in the data. We aim to make predictions made by a CNN interpretable. Hence, we present a novel framework called NeSyFOLD to create a neurosymbolic (NeSy) model for image classification tasks. The model is a CNN with all layers following the last convolutional layer replaced by a stratified answer set program (ASP). A rule-based machine learning algorithm called FOLD-SE-M is used to derive the stratified answer set program from binarized filter activations of the last convolutional layer. The answer set program can be viewed as a rule-set, wherein the truth value of each predicate depends on the activation of the corresponding kernel in the CNN. The rule-set serves as a global explanation for the model and is interpretable. A justification for the predictions made by the NeSy model can be obtained using an ASP interpreter. We also use our NeSyFOLD framework with a CNN that is trained using a sparse kernel learning technique called Elite BackProp (EBP). This leads to a significant reduction in rule-set size without compromising accuracy or fidelity thus improving scalability of the NeSy model and interpretability of its rule-set. Evaluation is done on datasets with varied complexity and sizes. To make the rule-set more intuitive to understand, we propose a novel algorithm for labelling each kernel's corresponding predicate in the rule-set with the semantic concept(s) it learns. We evaluate the performance of our "semantic labelling algorithm" to quantify the efficacy of the semantic labelling for both the NeSy model and the NeSy-EBP model.

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。

↑