arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.07832cs.ARcs.LG
收藏

面向多类别少样本学习的基于NAND闪存非对称编码的高效可靠向量相似性搜索

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

National Taiwan University(台湾大学);Academia Sinica(中央研究院);Macronix International Co. Ltd.(旺宏电子股份有限公司)

Hao-Wei Chiang, Chi-Tse Huang, Hsiang-Yun Cheng, Po-Hao Tseng, Ming-Hsiu Lee, An-Yeu, Wu

AI总结:

针对多类别少样本学习中内存增强神经网络的MCAM硬件限制问题,提出多比特温度计编码、非对称向量相似性搜索和硬件感知训练方法,大幅提升搜索效率与系统准确率。

摘要:

尽管内存增强神经网络(MANNs)通过将深度神经网络与外部存储器集成,为少样本学习(FSL)提供了有效解决方案,但在多类别FSL场景中,由于支持向量数量庞大,容量需求和数据移动的能耗开销变得极高。各类内存内搜索方案应运而生,以提升MANNs的能效。基于NAND的多比特内容可寻址存储器(MCAM)凭借其高密度和大容量成为极具潜力的选择。尽管潜力可观,MCAM仍面临诸多限制,例如字线数量受限、量化等级有限,以及串电流变化、瓶颈效应等非理想效应,这些问题会导致准确率大幅下降。为解决这些问题,我们提出了若干创新方法。首先,多比特温度计编码(MTMC)利用MCAM的超大容量,通过累积编码规则提升向量精度,从而缓解瓶颈效应。其次,非对称向量相似性搜索(AVSS)在保持支持向量精度的同时降低查询向量精度,以此减少搜索迭代次数,提升多类别场景下的效率。最后,硬件感知训练(HAT)方法通过对MCAM的硬件特性建模来优化控制器训练,从而提升系统的可靠性。我们的集成框架最多可将搜索迭代次数减少32倍,并将整体准确率提升1.58%至6.94%。

英文摘要:

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%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑