用于弹性预测服务系统的Coded-InvNet
Coded-InvNet for Resilient Prediction Serving Systems
摘要:
受可逆函数的一种新的编码计算算法的启发,我们提出了一种新的方法来设计弹性预测服务系统,可以优雅地处理掉队者或节点故障。Coded-InvNet利用深度学习文献中的最新发现,如可逆神经网络,流形混合和域转换算法,确定跨机器学习和系统的有趣研究方向。我们的实验结果表明,Coded-InvNet可以优于现有的方法,特别是当计算资源开销低至10%。例如,在不知道10个工人中的哪一个将失败的情况下,我们的算法可以设计一个备份任务,以便它可以正确地恢复丢失的预测结果,准确率为85.9%,比之前的SOTA高出32.5%。
英文摘要:
Inspired by a new coded computation algorithm for invertible functions, we propose Coded-InvNet a new approach to design resilient prediction serving systems that can gracefully handle stragglers or node failures. Coded-InvNet leverages recent findings in the deep learning literature such as invertible neural networks, Manifold Mixup, and domain translation algorithms, identifying interesting research directions that span across machine learning and systems. Our experimental results show that Coded-InvNet can outperform existing approaches, especially when the compute resource overhead is as low as 10%. For instance, without knowing which of the ten workers is going to fail, our algorithm can design a backup task so that it can correctly recover the missing prediction result with an accuracy of 85.9%, significantly outperforming the previous SOTA by 32.5%.
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。