# Learning-Based Data Storage [Vision] (Technical Report)

arXiv: https://arxiv.org/abs/2206.05778 · HTML: https://mlsanity.com/paper/2206.05778/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 12 Jun 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [The Case for Learned Index Structures](https://mlsanity.com/paper/1712.01208/) (2017)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [Off-Policy Multi-Agent Decomposed Policy Gradients](https://mlsanity.com/paper/2007.12322/) (2020)
- [Neo: A Learned Query Optimizer](https://mlsanity.com/paper/1904.03711/) (2019)
- [Bao: Learning to Steer Query Optimizers](https://mlsanity.com/paper/2004.03814/) (2020)
- [DeepSecure: Scalable Provably-Secure Deep Learning](https://mlsanity.com/paper/1705.08963/) (2017)
- [ALEX: An Updatable Adaptive Learned Index](https://mlsanity.com/paper/1905.08898/) (2019)
- [An End-to-End Learning-based Cost Estimator](https://mlsanity.com/paper/1906.02560/) (2019)
- [Learning Multi-dimensional Indexes](https://mlsanity.com/paper/1912.01668/) (2019)
- [Deep Reinforcement Learning for Join Order Enumeration](https://mlsanity.com/paper/1803.00055/) (2018)
- [SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning](https://mlsanity.com/paper/1901.05152/) (2019)
- [QuickSel: Quick Selectivity Learning with Mixture Models](https://mlsanity.com/paper/1812.10568/) (2018)
- [Black or White? How to Develop an AutoTuner for Memory-based Analytics [Extended Version]](https://mlsanity.com/paper/2002.11780/) (2020)
- [One Model to Rule them All: Towards Zero-Shot Learning for Databases](https://mlsanity.com/paper/2105.00642/) (2021)
- [Neurostream: Scalable and Energy Efficient Deep Learning with Smart Memory Cubes](https://mlsanity.com/paper/1701.06420/) (2017)
- [Opportunistic View Materialization with Deep Reinforcement Learning](https://mlsanity.com/paper/1903.01363/) (2019)
- [Towards Robust Deep Neural Networks](https://mlsanity.com/paper/1810.11726/) (2018)
- [Scheduling OLTP Transactions via Machine Learning](https://mlsanity.com/paper/1903.02990/) (2019)
- [A Survey and Experimental Analysis of Distributed Subgraph Matching](https://mlsanity.com/paper/1906.11518/) (2019)

## Abstract (arXiv)

Deep neural network (DNN) and its variants have been extensively used for a wide spectrum of real applications such as image classification, face/speech recognition, fraud detection, and so on. In addition to many important machine learning tasks, as artificial networks emulating the way brain cells function, DNNs also show the capability of storing non-linear relationships between input and output data, which exhibits the potential of storing data via DNNs. We envision a new paradigm of data storage, "DNN-as-a-Database", where data are encoded in well-trained machine learning models. Compared with conventional data storage that directly records data in raw formats, learning-based structures (e.g., DNN) can implicitly encode data pairs of inputs and outputs and compute/materialize actual output data of different resolutions only if input data are provided. This new paradigm can greatly enhance the data security by allowing flexible data privacy settings on different levels, achieve low space consumption and fast computation with the acceleration of new hardware (e.g., Diffractive Neural Network and AI chips), and can be generalized to distributed DNN-based storage/computing. In this paper, we propose this novel concept of learning-based data storage, which utilizes a learning structure called learning-based memory unit (LMU), to store, organize, and retrieve data. As a case study, we use DNNs as the engine in the LMU, and study the data capacity and accuracy of the DNN-based data storage. Our preliminary experimental results show the feasibility of the learning-based data storage by achieving high (100%) accuracy of the DNN storage. We explore and design effective solutions to utilize the DNN-based data storage to manage and query relational tables. We discuss how to generalize our solutions to other data types (e.g., graphs) and environments such as distributed DNN storage/computing.