Efficient And Reliable Vector Similarity Search Using Asymmetric Encoding With Nand-flash For Many-class Few-shot Learning

Abstract

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 bottlen

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keychiang2024efficient

Related papers

• In-memory Nearest Neighbor Search With Fefet Multi-bit Content-addressable Memories (2020)11.85
• Semantically Constrained Memory Allocation (SCMA) For Embedding In Efficient Recommendation Systems (2021)0.00
• AMES: Asymmetric And Memory-efficient Similarity Estimation For Instance-level Retrieval (2024)9.70
• In-memory Realization Of In-situ Few-shot Continual Learning With A Dynamically Evolving Explicit Memory (2022)8.60
• Efficient Similarity-preserving Unsupervised Learning Using Modular Sparse Distributed Codes And Novelty-contingent Noise (2020)0.00
• From HNSW To Information-theoretic Binarization: Rethinking The Architecture Of Scalable Vector Search (2025)0.00
• Associative Memories To Accelerate Approximate Nearest Neighbor Search (2016)6.34
• FLASH: Randomized Algorithms Accelerated Over CPU-GPU For Ultra-high Dimensional Similarity Search (2017)9.23