With the increased adoption of machine learning (ML) across applications and disciplines, a strong synergy
between the database (DB) systems and ML communities has emerged. Steps involved in ML pipelines—such as
data preparation and cleaning, feature engineering, and management of the ML lifecycle—can benefit
significantly from advances in data management. For example, managing the ML lifecycle requires mechanisms
for modeling, storing, and querying ML artifacts in a robust, scalable, and auditable manner.
More recently, the advent of large language models (LLMs) and Retrieval-Augmented Generation (RAG) has
further intensified the need for high-performance data management infrastructures. Modern AI systems
increasingly rely on vector databases, efficient vector search, and scalable model serving. At the same
time, the rise of multimodal AI introduces demanding requirements for storing and querying images, audio,
video, and other complex data types, all while maintaining low latency and high throughput for end users.
In the opposite direction, ML techniques are now explored in core components of database systems, including
query optimization, indexing, storage layout, and self-tuning. Long-standing challenges in databases—such
as cardinality estimation, operator and plan selection, resource management, and other tasks traditionally
handled with extensive human expertise or rigid heuristics—increasingly benefit from learned models and
data-driven approaches.
DBML 2026 aims to bring together researchers and practitioners working at this intersection, providing a dedicated forum for DB-inspired and ML-inspired approaches that address challenges in either or both communities. We welcome work that combines the strengths of DB and ML, ranging from foundational techniques and system designs to practical applications and real-world deployments, including ML for scientific data and other data-intensive domains.
Information about previous editions can be found at
DBML 2025
DBML 2024,
DBML 2023, and
DBML 2022.
For questions regarding the workshop, please contact:
dbml26@googlegroups.com.
Topics of Interest
ML for Data Management and DBMS
- Learned data discovery, cleaning, and transformation
- ML-enabled data exploration and discovery in data lakes and lakehouses
- Learned database design, configuration, and tuning
- ML for query optimization, indexing, and storage/layout decisions
- Natural language interfaces for data (querying, exploration, summarization, assistants)
- Pretrained, foundation, and LLM-based models for data management
- Representation learning for data cleaning, preprocessing, and integration
- Benchmarking and evaluation of ML-enhanced data management and DBMS components
Data Management for ML and AI Systems
- Data collection, preparation, and governance for ML/LLM/RAG applications
- Data quality, robustness, provenance, and lineage for ML workflows
- Systems and storage for efficient training, inference, and model serving
- Vector databases, indexing, and hybrid query processing for embeddings
- Management of multimodal data (text, images, audio, video, etc.) for AI applications
- DB-inspired techniques for modeling, storage, and provenance of ML and AI artifacts
