# Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams

arXiv: https://arxiv.org/abs/2505.19561 · HTML: https://mlsanity.com/paper/2505.19561/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 56 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 15 of 15)

- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Communication-efficient distributed SGD with Sketching](https://mlsanity.com/paper/1903.04488/) (2019)
- [Hash Embeddings for Efficient Word Representations](https://mlsanity.com/paper/1709.03933/) (2017)
- [Associative Long Short-Term Memory](https://mlsanity.com/paper/1602.03032/) (2016)
- [Compressing Gradient Optimizers via Count-Sketches](https://mlsanity.com/paper/1902.00179/) (2019)
- [Experimental Analysis of Large-scale Learnable Vector Storage Compression](https://mlsanity.com/paper/2311.15578/) (2023)
- [Meta-Learning Neural Bloom Filters](https://mlsanity.com/paper/1906.04304/) (2019)
- [Improved Frequency Estimation Algorithms with and without Predictions](https://mlsanity.com/paper/2312.07535/) (2023)
- [Scaling Graph-based Semi Supervised Learning to Large Number of Labels Using Count-Min Sketch](https://mlsanity.com/paper/1310.2959/) (2013)
- [Count-Min: Optimal Estimation and Tight Error Bounds using Empirical Error Distributions](https://mlsanity.com/paper/1811.04150/) (2018)
- [Learning-Based Heavy Hitters and Flow Frequency Estimation in Streams](https://mlsanity.com/paper/2406.16270/) (2024)

## Built on by (most cited first, 1 of 1)

- [On the (Generative) Linear Sketching Problem](https://mlsanity.com/paper/2603.14474/) (2026)

## Abstract (arXiv)

Sketches, probabilistic structures for estimating item frequencies in infinite data streams with limited space, are widely used across various domains. Recent studies have shifted the focus from handcrafted sketches to neural sketches, leveraging memory-augmented neural networks (MANNs) to enhance the streaming compression capabilities and achieve better space-accuracy trade-offs.However, existing neural sketches struggle to scale across different data domains and space budgets due to inflexible MANN configurations. In this paper, we introduce a scalable MANN architecture that brings to life the it Lego sketch, a novel sketch with superior scalability and accuracy. Much like assembling creations with modular Lego bricks, the Lego sketch dynamically coordinates multiple memory bricks to adapt to various space budgets and diverse data domains. Our theoretical analysis guarantees its high scalability and provides the first error bound for neural sketch. Furthermore, extensive experimental evaluations demonstrate that the Lego sketch exhibits superior space-accuracy trade-offs, outperforming existing handcrafted and neural sketches. Our code is available at https://github.com/FFY0/LegoSketchICML.