arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.10546cs.LGcs.CL
收藏

基于权值插值的数据更新后向兼容性研究

Backward Compatibility During Data Updates by Weight Interpolation

Heidelberg University(海德堡大学);AWS AI Labs(AWS人工智能实验室)

Raphael Schumann, Elman Mansimov, Yi-An Lai, Nikolaos Pappas, Xibin Gao, Yi Zhang

摘要:

当更新机器学习驱动的应用时,模型预测的向后兼容性是期望的属性。它允许无缝地改进底层模型,而不会引入回归错误。在分类任务中,这些错误以负翻转的形式出现。这意味着旧模型正确分类的实例现在被更新的模型错误分类。这对这种系统的用户体验具有直接的负面影响,例如,频繁使用的语音助理查询突然被错误分类。更新模型的一个常见原因是当新的训练数据变得可用并且需要被合并时。简单地用更新的数据重新训练模型会引入不必要的负翻转。研究了数据更新过程中的回归问题,提出了后向兼容权值插值(BCWI)。这种方法在新旧模型的权重之间进行插值,我们在大量的实验中表明,它在不牺牲新模型精度的情况下减少了负翻转。BCWI是直接实现的,不会增加推理成本。我们还探索了在插值过程中使用重要性权重,并对多个新模型的权重进行平均,以进一步减少负翻转。

英文摘要:

Backward compatibility of model predictions is a desired property when updating a machine learning driven application. It allows to seamlessly improve the underlying model without introducing regression bugs. In classification tasks these bugs occur in the form of negative flips. This means an instance that was correctly classified by the old model is now classified incorrectly by the updated model. This has direct negative impact on the user experience of such systems e.g. a frequently used voice assistant query is suddenly misclassified. A common reason to update the model is when new training data becomes available and needs to be incorporated. Simply retraining the model with the updated data introduces the unwanted negative flips. We study the problem of regression during data updates and propose Backward Compatible Weight Interpolation (BCWI). This method interpolates between the weights of the old and new model and we show in extensive experiments that it reduces negative flips without sacrificing the improved accuracy of the new model. BCWI is straight forward to implement and does not increase inference cost. We also explore the use of importance weighting during interpolation and averaging the weights of multiple new models in order to further reduce negative flips.

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。

↑