机器学习(Machine Learning)是一个研究计算学习方法的国际论坛。该杂志发表文章,报告广泛的学习方法应用于各种学习问题的实质性结果。该杂志的特色论文描述研究的问题和方法,应用研究和研究方法的问题。有关学习问题或方法的论文通过实证研究、理论分析或与心理现象的比较提供了坚实的支持。应用论文展示了如何应用学习方法来解决重要的应用问题。研究方法论文改进了机器学习的研究方法。所有的论文都以其他研究人员可以验证或复制的方式描述了支持证据。论文还详细说明了学习的组成部分,并讨论了关于知识表示和性能任务的假设。 官网地址:http://dblp.uni-trier.de/db/journals/ml/

最新内容

As machine learning models grow more complex and their applications become more high-stakes, tools for explaining model predictions have become increasingly important. Despite the widespread use of explainability techniques, evaluating and comparing different feature attribution methods remains challenging: evaluations ideally require human studies, and empirical evaluation metrics are often computationally prohibitive on real-world datasets. In this work, we address this issue by releasing XAI-Bench: a suite of synthetic datasets along with a library for benchmarking feature attribution algorithms. Unlike real-world datasets, synthetic datasets allow the efficient computation of conditional expected values that are needed to evaluate ground-truth Shapley values and other metrics. The synthetic datasets we release offer a wide variety of parameters that can be configured to simulate real-world data. We demonstrate the power of our library by benchmarking popular explainability techniques across several evaluation metrics and identifying failure modes for popular explainers. The efficiency of our library will help bring new explainability methods from development to deployment.

0
0
下载
预览

最新论文

As machine learning models grow more complex and their applications become more high-stakes, tools for explaining model predictions have become increasingly important. Despite the widespread use of explainability techniques, evaluating and comparing different feature attribution methods remains challenging: evaluations ideally require human studies, and empirical evaluation metrics are often computationally prohibitive on real-world datasets. In this work, we address this issue by releasing XAI-Bench: a suite of synthetic datasets along with a library for benchmarking feature attribution algorithms. Unlike real-world datasets, synthetic datasets allow the efficient computation of conditional expected values that are needed to evaluate ground-truth Shapley values and other metrics. The synthetic datasets we release offer a wide variety of parameters that can be configured to simulate real-world data. We demonstrate the power of our library by benchmarking popular explainability techniques across several evaluation metrics and identifying failure modes for popular explainers. The efficiency of our library will help bring new explainability methods from development to deployment.

0
0
下载
预览
Top