论文标题
Omnixai：可解释AI的库
OmniXAI: A Library for Explainable AI
论文作者
论文摘要
我们介绍了Omnixai（Omni Audentable AI的缩写），这是一个可解释的AI（XAI）的开源Python库，它提供了可解释的AI功能和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）在实践中做出的决策的痛苦点。 Omnixai的目标是成为一个一站式综合库，它使数据科学家，ML研究人员和从业人员易于解释，他们需要在ML过程的不同阶段（数据探索，功能工程，模型开发，评估，评估和决策和制造等）对各种类型的数据，模型和解释方法进行解释）。特别是，我们的库包括集成在统一界面中的丰富的解释方法，该方法支持多种数据类型（表格数据，图像，文本，文本，时间序列），多种类型的ML模型（Scikit-Learn中的传统ML和Pytorch/Tensorflow中的深度学习模型），以及包括“模型”（包括“模型）”和“模型”（包括“模型）”（包括“模型）”和“和“模型）”和“和aggib”的范围（又是“和agg”）。解释，反事实解释，基于梯度的解释等）。对于从业者来说，图书馆提供了一个易于使用的统一界面，仅通过编写几行代码来生成其应用程序的解释，也提供了一个GUI仪表板，用于可视化不同的解释，以提供有关决策的更多见解。在此技术报告中，我们介绍了Omnixai的设计原理，系统体系结构和主要功能，并且还展示了不同类型的数据，任务和模型的几个示例用例。
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.
