用文本生成文本预测大规模系统性能，效果远超传统方法。
Performance Prediction for Large Systems via Text-to-Text Regression
- 直接用系统日志等文本数据做回归预测，免去复杂特征工程。
- 在谷歌Borg集群上实现0.99的排名相关性，误差比传统方法低100倍。
- 只需500个样本就能快速适应新任务，还能捕捉复杂结果分布。
在多个行业中，预测大型系统的指标表现是一个核心问题，传统上依赖表格回归。然而，面对配置文件或系统日志等复杂真实数据，特征工程常难以实施。本文提出文本到文本回归作为通用且可扩展的替代方案。针对谷歌大规模计算集群调度系统Borg的资源效率预测，一个6000万参数的编码器-解码器模型，从随机初始化训练，在整个集群上实现了高达0.99（平均0.9）的排名相关性，均方误差比表格方法低100倍。该模型仅需500个少样本即可快速适配新任务，并能捕捉复杂结果分布的密度。消融实验表明，使用编码器、增加序列长度以及模型固有的不确定性量化至关重要。这些发现为现实世界结果的通用模拟器铺平了道路。
原文摘要 · Abstract (English)
In many industries, predicting metric outcomes of large systems is a fundamental problem, driven largely by traditional tabular regression. However, such methods struggle on complex systems data in the wild such as configuration files or system logs, where feature engineering is often infeasible. We propose text-to-text regression as a general, scalable alternative. For predicting resource efficiency on Borg, Google's massive compute cluster scheduling system, a 60M parameter encoder-decoder, trained from random initialization, achieves up to a near perfect 0.99 (0.9 average) rank correlation across the entire fleet, and 100x lower MSE than tabular approaches. The model also easily adapts to new tasks in only 500 few-shot examples and captures the densities of complex outcome distributions. Ablation studies highlight the importance of using encoders, increasing sequence length, and the model's inherent uncertainty quantification. These findings pave the way for universal simulators of real-world outcomes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。