One Model to Rule them All: Towards Zero-Shot Learning for Databases
This work addresses the challenge of reducing training overhead for database components, offering a potential solution for database administrators and developers, though it is incremental as it builds on existing transfer learning concepts.
The paper tackles the problem of adapting machine learning models to new databases without retraining, proposing zero-shot learning for databases and demonstrating its feasibility for physical cost estimation with promising initial results.
In this paper, we present our vision of so called zero-shot learning for databases which is a new learning approach for database components. Zero-shot learning for databases is inspired by recent advances in transfer learning of models such as GPT-3 and can support a new database out-of-the box without the need to train a new model. Furthermore, it can easily be extended to few-shot learning by further retraining the model on the unseen database. As a first concrete contribution in this paper, we show the feasibility of zero-shot learning for the task of physical cost estimation and present very promising initial results. Moreover, as a second contribution we discuss the core challenges related to zero-shot learning for databases and present a roadmap to extend zero-shot learning towards many other tasks beyond cost estimation or even beyond classical database systems and workloads.