机器学习系统向后兼容性的实证分析
An Empirical Analysis of Backward Compatibility in Machine Learning Systems
摘要:
在机器学习(ML)的许多应用中,更新的目的是提高模型的性能。然而,当前更新模型的实践仅依赖于孤立的聚合性能分析,忽略了实际部署中的重要依赖关系、期望和需求。我们考虑旨在改进ML模型的更新如何引入新的错误,这些错误可能会严重影响下游系统和用户。例如,基于云的分类服务(如图像识别)中使用的模型的更新可能会在调用服务的系统中导致意外的错误行为。先前的工作已经表明了“向后兼容性”对于维护人类信任的重要性。我们研究了不同ML架构和数据集之间向后兼容性的挑战,重点关注常见的设置,包括结构化噪声和推理管道中使用的ML的数据偏移。我们的研究结果表明:(i)由于优化随机性,即使没有数据偏移,也会出现兼容性问题;(ii)即使模型精度提高,在大规模噪声数据集上进行训练也会导致向后兼容性显着降低;(iii)不兼容点的分布与噪声偏差一致,因此需要兼容性感知的去噪和鲁棒性方法。
英文摘要:
In many applications of machine learning (ML), updates are performed with the goal of enhancing model performance. However, current practices for updating models rely solely on isolated, aggregate performance analyses, overlooking important dependencies, expectations, and needs in real-world deployments. We consider how updates, intended to improve ML models, can introduce new errors that can significantly affect downstream systems and users. For example, updates in models used in cloud-based classification services, such as image recognition, can cause unexpected erroneous behavior in systems that make calls to the services. Prior work has shown the importance of "backward compatibility" for maintaining human trust. We study challenges with backward compatibility across different ML architectures and datasets, focusing on common settings including data shifts with structured noise and ML employed in inferential pipelines. Our results show that (i) compatibility issues arise even without data shift due to optimization stochasticity, (ii) training on large-scale noisy datasets often results in significant decreases in backward compatibility even when model accuracy increases, and (iii) distributions of incompatible points align with noise bias, motivating the need for compatibility aware de-noising and robustness methods.
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。