一种用于深度学习模型事后解释与关联的重描述挖掘框架
A redescription mining framework for post-hoc explaining and relating deep learning models
AI总结:
本文提出一种基于重描述挖掘的事后解释框架,通过识别神经元激活的统计显著重描述,对任意深度学习模型进行队列分析、层间关联和跨模型关联,从而提升模型可解释性。
摘要:
深度学习模型(DLMs)在结构化数据和非结构化数据上均取得了越来越高的性能,显著扩展了机器学习在各个领域的适用性。它们在预测、模式发现和新数据生成方面的成功对科学和工业产生了重要影响。尽管取得了这些成就,但由于其规模庞大,DLMs 难以解释。在本工作中,我们提出了一种新颖的框架,利用重描述对 DLMs 进行事后解释和关联。该框架通过识别神经元激活的统计显著重描述,支持对任意 DLMs 进行队列分析。它能够将神经元与一组目标标签或一组描述性属性耦合,关联单个 DLM 内的不同层,或关联不同的 DLMs。所提出的框架独立于人工神经网络架构,并且可以处理更复杂的目标标签(例如多标签或多目标场景)。此外,它能够同时模拟教学式规则提取方法和分解式规则提取方法。与现有的可解释人工智能方法相比,所提出框架的上述特性可以通过提供不同的信息来提高任意 DLMs 的可解释性和可理解性。
英文摘要:
Deep learning models (DLMs) achieve increasingly high performance both on structured and unstructured data. They significantly extended applicability of machine learning to various domains. Their success in making predictions, detecting patterns and generating new data made significant impact on science and industry. Despite these accomplishments, DLMs are difficult to explain because of their enormous size. In this work, we propose a novel framework for post-hoc explaining and relating DLMs using redescriptions. The framework allows cohort analysis of arbitrary DLMs by identifying statistically significant redescriptions of neuron activations. It allows coupling neurons to a set of target labels or sets of descriptive attributes, relating layers within a single DLM or associating different DLMs. The proposed framework is independent of the artificial neural network architecture and can work with more complex target labels (e.g. multi-label or multi-target scenario). Additionally, it can emulate both pedagogical and decompositional approach to rule extraction. The aforementioned properties of the proposed framework can increase explainability and interpretability of arbitrary DLMs by providing different information compared to existing explainable-AI approaches.
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。