利用重心思想修复神经网络权重故障，无需重训即可大幅提高可靠性。
CoG-Guided Weight Correction for Fault-Tolerant Deep Neural Networks
- 基于权重空间分布的重心机制，动态识别并修正故障值。
- 在10^{-3}位错误率下，性能提升最高达230倍，精度损失极小。
- 适用于医疗等安全关键场景，尤其适合部署受限的模型。
用于安全关键应用的深度神经网络易受硬件与内存故障影响，导致权重损坏、可靠性下降。本文提出一种基于中心点（CoG）的权重修正方法，利用每层权重的空间特性进行故障检测与修复，采用距离感知的修正规则，无需重训或修改结构。通过在不同位错误率（BER）下注入故障，验证了该方法在容错能力上的有效性。实验表明，在基于LSTM的安全关键网络中，StageNet（疾病进展追踪）和MTFNet（心脏异常检测）在10^{-3} BER下分别实现高达230倍和6.41倍的容错提升，且精度损失可忽略。扩展至卷积神经网络时，ResNet-18与VGG-16在相似故障条件下分别提升49.55倍和20.79倍。据我们所知，这是首个将CoG概念应用于神经网络权重张量以增强可靠性的研究。
原文摘要 · Abstract (English)
Deep Neural Networks (DNNs) used in safety-critical applications are vulnerable to hardware and memory faults that corrupt network weights and degrade reliability. In this paper, we propose a Center of Gravity (CoG) guided weight correction method that restores faulty weights based on their spatial characteristics within each layer. The proposed approach detects and corrects weight faults using distance-aware correction rules, eliminating the need for retraining or architectural modification. The effectiveness of the proposed method in terms of the capability of tolerating hardware faults has been evaluated through performing fault injection at different Bit Error Rates (BERs). Experiments on safety-critical LSTM-based Networks, including StageNet for disease progression tracking and MTFNet for cardiac anomaly detection, demonstrate fault tolerance improvements of up to 230x and 6.41x, respectively, at a BER of 10^{-3}, with negligible accuracy loss. When extended to Convolutional Neural Networks (CNNs), the method achieves up to 49.55x and 20.79x improvements under comparable fault conditions on ResNet-18 and VGG-16, respectively. To the best of our knowledge, this is the first work to apply the CoG concept to neural network weight tensors for enhancing model reliability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。