# Efficient and Reliable Vector Similarity Search Using Asymmetric Encoding with NAND-Flash for Many-Class Few-Shot Learning

arXiv: https://arxiv.org/abs/2409.07832 · HTML: https://mlsanity.com/paper/2409.07832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 12 Sep 2024.

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

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2003.04390/) (2020)
- [Charting the Right Manifold: Manifold Mixup for Few-shot Learning](https://mlsanity.com/paper/1907.12087/) (2019)
- [Negative Margin Matters: Understanding Margin in Few-shot Classification](https://mlsanity.com/paper/2003.12060/) (2020)
- [Learning to Remember Rare Events](https://mlsanity.com/paper/1703.03129/) (2017)
- [Robust High-dimensional Memory-augmented Neural Networks](https://mlsanity.com/paper/2010.01939/) (2020)
- [Enhanced Few-shot Learning for Intrusion Detection in Railway Video Surveillance](https://mlsanity.com/paper/2011.04254/) (2020)
- [Show and Grasp: Few-shot Semantic Segmentation for Robot Grasping through Zero-shot Foundation Models](https://mlsanity.com/paper/2404.12717/) (2024)
- [Gradient-based Bit Encoding Optimization for Noise-Robust Binary Memristive Crossbar](https://mlsanity.com/paper/2201.01479/) (2022)

## Abstract (arXiv)

While memory-augmented neural networks (MANNs) offer an effective solution for few-shot learning (FSL) by integrating deep neural networks with external memory, the capacity requirements and energy overhead of data movement become enormous due to the large number of support vectors in many-class FSL scenarios. Various in-memory search solutions have emerged to improve the energy efficiency of MANNs. NAND-based multi-bit content addressable memory (MCAM) is a promising option due to its high density and large capacity. Despite its potential, MCAM faces limitations such as a restricted number of word lines, limited quantization levels, and non-ideal effects like varying string currents and bottleneck effects, which lead to significant accuracy drops. To address these issues, we propose several innovative methods. First, the Multi-bit Thermometer Code (MTMC) leverages the extensive capacity of MCAM to enhance vector precision using cumulative encoding rules, thereby mitigating the bottleneck effect. Second, the Asymmetric vector similarity search (AVSS) reduces the precision of the query vector while maintaining that of the support vectors, thereby minimizing the search iterations and improving efficiency in many-class scenarios. Finally, the Hardware-Aware Training (HAT) method optimizes controller training by modeling the hardware characteristics of MCAM, thus enhancing the reliability of the system. Our integrated framework reduces search iterations by up to 32 times, and increases overall accuracy by 1.58% to 6.94%.