用近似计算提升可解释AI能效，让边缘设备实时解释模型决策。
ApproXAI: Energy-Efficient Hardware Acceleration of Explainable AI using Approximate Computing
- 将可解释AI算法转为近似矩阵运算，结合卷积与傅里叶变换。
- 在TPU边缘设备上实现能效翻倍，准确率接近精确方法。
- 适合能源受限的实时可解释AI部署场景。
可解释人工智能（XAI）通过将可解释性建模为优化问题来增强AI系统的透明度。然而，该方法通常需要大量计算密集型迭代操作，限制了其在实时场景中的应用。尽管已有研究在FPGA和TPU上进行XAI硬件加速，但未能充分解决实时环境下的能效问题。为此，我们提出XAIedge框架，将近似计算技术融入集成梯度、模型蒸馏和Shapley分析等XAI算法中。XAIedge将这些算法转化为近似矩阵计算，并利用卷积、傅里叶变换与近似计算范式之间的协同效应，在基于TPU的边缘设备上实现高效硬件加速，支持快速实时结果解释。全面评估表明，XAIedge相比现有精确XAI硬件加速技术实现2倍能效提升，同时保持相当的准确性。这凸显了XAIedge在能源受限实时应用中推动可解释AI部署的巨大潜力。
原文摘要 · Abstract (English)
Explainable artificial intelligence (XAI) enhances AI system transparency by framing interpretability as an optimization problem. However, this approach often necessitates numerous iterations of computationally intensive operations, limiting its applicability in real-time scenarios. While recent research has focused on XAI hardware acceleration on FPGAs and TPU, these methods do not fully address energy efficiency in real-time settings. To address this limitation, we propose XAIedge, a novel framework that leverages approximate computing techniques into XAI algorithms, including integrated gradients, model distillation, and Shapley analysis. XAIedge translates these algorithms into approximate matrix computations and exploits the synergy between convolution, Fourier transform, and approximate computing paradigms. This approach enables efficient hardware acceleration on TPU-based edge devices, facilitating faster real-time outcome interpretations. Our comprehensive evaluation demonstrates that XAIedge achieves a $2\times$ improvement in energy efficiency compared to existing accurate XAI hardware acceleration techniques while maintaining comparable accuracy. These results highlight the potential of XAIedge to significantly advance the deployment of explainable AI in energy-constrained real-time applications.
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。