We introduce OmniXAI (short for Omni eXplainable AI), an open-source Python library of eXplainable AI (XAI), which offers omni-way explainable AI capabilities and various interpretable machine learning techniques to address the pain points of understanding and interpreting the decisions made by machine learning (ML) in practice. OmniXAI aims to be a one-stop comprehensive library that makes explainable AI easy for data scientists, ML researchers and practitioners who need explanation for various types of data, models and explanation methods at different stages of ML process (data exploration, feature engineering, model development, evaluation, and decision-making, etc). In particular, our library includes a rich family of explanation methods integrated in a unified interface, which supports multiple data types (tabular data, images, texts, time-series), multiple types of ML models (traditional ML in Scikit-learn and deep learning models in PyTorch/TensorFlow), and a range of diverse explanation methods including "model-specific" and "model-agnostic" ones (such as feature-attribution explanation, counterfactual explanation, gradient-based explanation, etc). For practitioners, the library provides an easy-to-use unified interface to generate the explanations for their applications by only writing a few lines of codes, and also a GUI dashboard for visualization of different explanations for more insights about decisions. In this technical report, we present OmniXAI's design principles, system architectures, and major functionalities, and also demonstrate several example use cases across different types of data, tasks, and models.
翻译:我们引入OmniXAI(Omni eXplaive AI (XAI),这是一个开放源代码 Python 图书馆,它提供全路可解释的AI 能力以及各种可解释的机器学习技术,以解决理解和解释机器学习(ML)所作决定的疼痛点。OmniXAI 旨在成为一个一站式的综合图书馆,使数据科学家、ML研究人员和从业人员在ML进程的不同阶段(数据探索、特征工程、模型开发、评估和决策等)需要解释各种类型的数据、模型和解释方法能够容易解释。 特别是,我们的图书馆图书馆拥有丰富的解释方法,支持多种类型的数据(数据、图像、文本、时间序列)、多种类型的ML模型(Scikit-learn和PyTorrichor Flow的传统的传统的传统 MLLL),以及一系列不同的解释方法,包括“模型-特定”和“模型-Agreat-agnological ”, 用于本系统内部的简单解释, 解释(例如) 直观解释、直观解释、直观解释、直观解释、直观解释、直观解释、直观解释的多种数据-直径解释,以及直径解释,也提供的系统、直径解释,以及直径解释,也提供、直径解释、直径解释,以及直径解释,也提供、直径解释、直径解释、直径解的多个解释、直径解释,也提供的、直径解释,以及直径解释,也提供不同解释,也提供的多个解释。