针对 Microsoft 365 云系统故障预测中数据缺失影响性能的问题,提出样本高效的扩散模型 Diffusion+ 进行时间序列数据插补,有效提升了下游故障预测任务的性能。
摘要:
可靠性对于像 Microsoft 365 这样的大规模云系统极为重要。磁盘故障、节点故障等云故障威胁着服务可靠性,导致在线服务中断和经济损失。现有工作侧重于预测云故障并在故障发生前主动采取行动。然而,它们在模型训练和预测中受困于数据缺失等数据质量差的问题,这限制了性能。在本文中,我们专注于通过所提出的 Diffusion+(一种样本高效的扩散模型)进行数据插补来提升数据质量,基于观测数据高效地插补缺失数据。我们的实验和应用实践表明,我们的模型有助于提升下游故障预测任务的性能。
英文摘要:
Reliability is extremely important for large-scale cloud systems like Microsoft 365. Cloud failures such as disk failure, node failure, etc. threaten service reliability, resulting in online service interruptions and economic loss. Existing works focus on predicting cloud failures and proactively taking action before failures happen. However, they suffer from poor data quality like data missing in model training and prediction, which limits the performance. In this paper, we focus on enhancing data quality through data imputation by the proposed Diffusion+, a sample-efficient diffusion model, to impute the missing data efficiently based on the observed data. Our experiments and application practice show that our model contributes to improving the performance of the downstream failure prediction task.
Extended Missing Data Imputation via GANs for Ranking Applications
Cornell University(康奈尔大学);Amazon(亚马逊)
我们提出了条件填补GAN,一种基于生成对抗网络(GANs)的扩展缺失数据填补方法。激励用例是学习排名,现代搜索,推荐系统和信息检索应用程序的基石。经验排序数据集并不总是遵循标准高斯分布或完全随机缺失(MCAR)机制,这是经典缺失数据插补方法的标准假设。我们的方法提供了一个简单的解决方案,提供兼容的插补保证,同时放松假设缺失的机制和回避近似棘手的分布,以提高插补质量。我们证明了最佳的GAN填补实现扩展随机缺失(EMAR)和扩展总是随机缺失(EAMAR)机制,超越了天真的MCAR。我们的方法在开源Microsoft Research Ranking(MSR)数据集和合成排名数据集上展示了最高的插补质量,与最先进的基准和各种特征分布相比。使用专有的Amazon Search排名数据集,我们还展示了与地面实况数据相比,在GAN估算数据上训练的排名模型的可比排名质量指标。
PAMF: Prior-Aware Multimodal Fusion for Incomplete Time Series Data
Department of Computer Science, University of Central Florida(中央佛罗里达大学计算机科学系);Department of Computer Science, University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校计算机科学系)
Cross-Domain Conditional Diffusion Models for Time Series Imputation
Northwestern University(西北大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Arizona State University(亚利桑那州立大学);Virginia Tech(弗吉尼亚理工学院);Squirrel Ai Learning
TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data
Boundary-enhanced time series data imputation with long-term dependency diffusion models
Henan University(河南大学);Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China(电子科技大学长三角研究院(衢州));University College London(伦敦大学学院)
Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspective
State Key Lab of General AI, School of Intelligence Science and Technology, Peking University(人工智能国家重点实验室、智能科学与技术学院、北京大学);Zhejiang University(浙江大学);Beijing Academy of Artificial Intelligence (BAAI)(北京人工智能研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Center for Data Science, Peking University(北京大学数据科学中心);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Pazhou Laboratory (Huangpu), Guangzhou, China(黄埔实验室(华南))
Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation
Central South University(中南大学);Aalborg University(奥尔堡大学);The Hong Kong Polytechnic University(香港理工大学);National University of Defense Technology(国防科技大学)
Well log data generation and imputation using sequence-based generative adversarial networks
College of Petroleum Engineering and Geosciences(石油工程与地球科学学院);King Fahd University of Petroleum & Minerals(法赫德国王石油与矿产大学);University, Stanford(斯坦福大学);SDAIA-KFUPM Joint Research Center for Artificial Intelligence(SDAIA-KFUPM人工智能联合研究中心)