Delta Tensor: Efficient Vector and Tensor Storage in Delta Lake
This work addresses storage bottlenecks for data-intensive AI/ML applications in cloud-native environments, though it appears incremental as it adapts existing array database strategies to Delta Lake.
The paper tackled the problem of efficiently storing vector and tensor data in AI/ML applications by proposing a novel approach using Delta Lake in a Lakehouse architecture, resulting in notable improvements in space and time efficiencies compared to traditional serialization methods.
The exponential growth of artificial intelligence (AI) and machine learning (ML) applications has necessitated the development of efficient storage solutions for vector and tensor data. This paper presents a novel approach for tensor storage in a Lakehouse architecture using Delta Lake. By adopting the multidimensional array storage strategy from array databases and sparse encoding methods to Delta Lake tables, experiments show that this approach has demonstrated notable improvements in both space and time efficiencies when compared to traditional serialization of tensors. These results provide valuable insights for the development and implementation of optimized vector and tensor storage solutions in data-intensive applications, contributing to the evolution of efficient data management practices in AI and ML domains in cloud-native environments