Virtual indexes play a crucial role in database query optimization. However, with the rapid advancement of cloud computing and AI-driven models for database optimization, traditional virtual index approaches face significant challenges. Cloud-native environments often prohibit direct conducting query optimization process on production databases due to stability requirements and data privacy concerns. Moreover, while AI models show promising progress, their integration with database systems poses challenges in system complexity, inference acceleration, and model hot updates. In this paper, we present VIDEX, a three-layer disaggregated architecture that decouples database instances, the virtual index optimizer, and algorithm services, providing standardized interfaces for AI model integration. Users can configure VIDEX by either collecting production statistics or loading from a prepared file, enabling high-accuracy what-if analysis using virtual indexes that yield query plans identical to production instances. Additionally, users can freely integrate new AI-driven algorithms into VIDEX. VIDEX has been deployed at ByteDance, serving thousands of MySQL instances daily and over millions of SQL queries for index optimization tasks.

Estimating the Number of Distinct Values (NDV) is fundamental for numerous data management tasks, especially within database applications. However, most existing works primarily focus on introducing new statistical or learned estimators, while identifying the most suitable estimator for a given scenario remains largely unexplored. Therefore, we propose AdaNDV, a learned method designed to adaptively select and fuse existing estimators to address this issue. Specifically, (1) we propose to use learned models to distinguish between overestimated and underestimated estimators and then select appropriate estimators from each category. This strategy provides a complementary perspective by integrating overestimations and underestimations for error correction, thereby improving the accuracy of NDV estimation. (2) To further integrate the estimation results, we introduce a novel fusion approach that employs a learned model to predict the weights of the selected estimators and then applies a weighted sum to merge them. By combining these strategies, the proposed AdaNDV fundamentally distinguishes itself from previous works that directly estimate NDV. Moreover, extensive experiments conducted on real-world datasets, with the number of individual columns being several orders of magnitude larger than in previous studies, demonstrate the superior performance of our method.

To ensure the security and stabilization of the communication networks, anomaly detection is the first line of defense. However, their learning process suffers two major issues: (1) inadequate labels : there are many different kinds of attacks but rare abnormal nodes in mt of these atstacks; and (2) inaccurate labels : considering the heavy network flows and new emerging attacks, providing accurate labels for all nodes is very expensive. The inadequate and inaccurate label problem challenges many existing methods because the majority normal nodes result in a biased classifier while the noisy labels will further degrade the performance of the classifier. To tackle these issues, we propose SemiADC, a Semi -supervised A nomaly D etection framework for dynamic C ommunication networks. SemiADC first approximately learns the feature distribution of normal nodes with regularization from abnormal ones. It then cleans the datasets and extracts the nodes sasainaccurate labels by the learned feature distribution and structure-based temporal correlations. These self-learning processes run iteratively with mutual promotion, and finally help increase the accuracy of anomaly detection. Experimental evaluations on real-world datasets demonstrate the effectiveness of our SemiADC, which performs substantially better than the state-of-art anomaly detection approaches without the demand of adequate and accurate supervision.