{"ID":2836295,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21160","arxiv_id":"2511.21160","title":"MorphingDB: A Task-Centric AI-Native DBMS for Model Management and Inference","abstract":"The increasing demand for deep neural inference within database environments has driven the emergence of AI-native DBMSs. However, existing solutions either rely on model-centric designs requiring developers to manually select, configure, and maintain models, resulting in high development overhead, or adopt task-centric AutoML approaches with high computational costs and poor DBMS integration. We present MorphingDB, a task-centric AI-native DBMS that automates model storage, selection, and inference within PostgreSQL. To enable flexible, I/O-efficient storage of deep learning models, we first introduce specialized schemas and multi-dimensional tensor data types to support BLOB-based all-in-one and decoupled model storage. Then we design a transfer learning framework for model selection in two phases, which builds a transferability subspace via offline embedding of historical tasks and employs online projection through feature-aware mapping for real-time tasks. To further optimize inference throughput, we propose pre-embedding with vectoring sharing to eliminate redundant computations and DAG-based batch pipelines with cost-aware scheduling to minimize the inference time. Implemented as a PostgreSQL extension with LibTorch, MorphingDB outperforms AI-native DBMSs (EvaDB, Madlib, GaussML) and AutoML platforms (AutoGluon, AutoKeras, AutoSklearn) across nine public datasets, encompassing series, NLP, and image tasks. Our evaluation demonstrates a robust balance among accuracy, resource consumption, and time cost in model selection and significant gains in throughput and resource efficiency.","short_abstract":"The increasing demand for deep neural inference within database environments has driven the emergence of AI-native DBMSs. However, existing solutions either rely on model-centric designs requiring developers to manually select, configure, and maintain models, resulting in high development overhead, or adopt task-centri...","url_abs":"https://arxiv.org/abs/2511.21160","url_pdf":"https://arxiv.org/pdf/2511.21160v1","authors":"[\"Wu Sai\",\"Xia Ruichen\",\"Yang Dingyu\",\"Wang Rui\",\"Lai Huihang\",\"Guan Jiarui\",\"Bai Jiameng\",\"Zhang Dongxiang\",\"Tang Xiu\",\"Xie Zhongle\",\"Lu Peng\",\"Chen Gang\"]","published":"2025-11-26T08:19:53Z","proceeding":"cs.DB","tasks":"[\"cs.DB\"]","methods":"[]","has_code":false}