Relational database management systems (RDBMSs) employ query optimizers to search for execution plans deemed optimal for specific queries. Classical optimizers rely on inaccurate parameter estimates and assumptions that may not hold true in real-world scenarios. Consequently, suboptimal execution plans may be chosen, leading to poor query execution performance. Recent proposals of learned query optimizers that leverage Machine Learning suffer also from the selection of suboptimal plans. In order to fill this gap, we have created Robust Workload Optimization (RobOpt), a prototype tool that facilitates robust execution of a query workload in RDBMSs. It implements a novel technique that takes workload logs as input, generates training samples, and trains a risk-aware learned cost model. It optimizes risk-aware plan selection strategies to achieve a desired level of runtime performance and robustness. In addition, it analyzes a workload according to its training samples and determines an optimal plan selection strategy either at the workload or query level. Ultimately, it enables the robust execution of any workload by determining an optimal plan selection strategy per query. RobOpt can work on top of any RDBMS.
The generation of large amounts of healthcare data has motivated the use of Machine Learning (ML) to train robust models for clinical tasks. However, limitations of local datasets and restrictions on sharing patient data impede the use of traditional ML workflows. Consequently, Federated Learning (FL) has emerged as a potential solution for training ML models among multiple healthcare centers. In this study, we focus on the binary classification task of early ICU mortality prediction using Multivariate Time Series data and a deep neural network architecture. We evaluate the performance of two FL algorithms (FedAvg and FedProx) on this task, utilizing a real world multi-center benchmark database. Our results show that FL models outperform local ML models in a realistic scenario with non-identically distributed data, thus indicating that FL is a promising solution for analogous problems within the healthcare domain. Nevertheless, in this experimental scenario, they do not approximate the ideal performance of a centralized ML model.
2 April 2026 in Proceedings of the ACM on Management of Data
Although machine learning (ML) shows potential in improving query optimization by generating and selecting more efficient plans, ensuring the robustness of learning-based cost models (LCMs) remains challenging. These LCMs currently lack explainability, which undermines user trust and limits the ability to derive insights from their cost predictions to improve plan quality. Accurately converting tree-structured query plans into representations via tree models is also essential, as omitting any details may negatively impact subsequent cost model performance. Additionally, inherent uncertainty in cost estimation leads to inaccurate predictions, resulting in suboptimal plan selection. To address these challenges, we introduce Reqo, a R obust and E xplainable Q uery O ptimization cost model that comprehensively enhances three main stages in query optimization: plan generation, plan representation, and plan selection. Reqo integrates three innovations: the first explainability technique for LCMs that quantifies subgraph contributions and produces plan generation hints to enhance candidate plan quality; a novel tree model based on Bidirectional Graph Neural Networks (Bi-GNNs) with a Gated Recurrent Unit (GRU) aggregator to further capture both node-level and structural information and effectively strengthen plan representation; and an uncertainty-aware learning-to-rank cost estimator that adaptively integrates cost estimates with uncertainties to enhance plan selection robustness. Extensive experiments demonstrate that Reqo outperforms state-of-the-art approaches across all three stages.