Enabling SQL-based Training Data Debugging for Federated Learning

no code implementations • 26 Aug 2021 • Yejia Liu, Weiyuan Wu, Lampros Flokas, Jiannan Wang, Eugene Wu

The SQL-based training data debugging framework has proved effective to fix this kind of issue in a non-federated learning setting.

Federated Learning

Explaining Inference Queries with Bayesian Optimization

1 code implementation • 10 Feb 2021 • Brandon Lockhart, Jinglin Peng, Weiyuan Wu, Jiannan Wang, Eugene Wu

BO - a technique for finding the global optimum of a black-box function - is used to find the best predicate.

Bayesian Optimization

Are We Ready For Learned Cardinality Estimation?

2 code implementations • 12 Dec 2020 • Xiaoying Wang, Changbo Qu, Weiyuan Wu, Jiannan Wang, Qingqing Zhou

The results show that learned models are indeed more accurate than traditional methods, but they often suffer from high training and inference costs.

Complaint-driven Training Data Debugging for Query 2.0

1 code implementation • 12 Apr 2020 • Weiyuan Wu, Lampros Flokas, Eugene Wu, Jiannan Wang

As the need for machine learning (ML) increases rapidly across all industry sectors, there is a significant interest among commercial database providers to support "Query 2. 0", which integrates model inference into SQL queries.