动态神经网络+量化策略，让移动设备省电80%完成多传感器融合推理
Resource-Efficient Sensor Fusion via System-Wide Dynamic Gated Neural Networks
- 用带分支的动态神经网络按需调用传感器与计算资源
- 在RADIATE数据集上推理能耗降低超80%，接近理论最优
- 首次将动态网络与系统级决策结合，适合边缘AI部署
移动系统需支持多个基于AI的应用，各自通过异构数据源（雷达、激光雷达、摄像头）利用协同执行的深度神经网络（DNN）完成推理。为在延迟、质量及推理可靠性约束下最小化推理能耗，必须优化传感器选择、DNN结构、网络节点分配和资源使用。本文提出基于分位数约束策略优化的量化约束推理（QIC）算法，联合决策上述四方面，以最小化能耗。首次将动态门控DNN与基础设施级决策结合。在包含真实无线测量的RADIATE数据集上，基于带主干和分支的动态DNN进行训练，实验表明QIC性能接近最优，相比替代方案节能超80%。
原文摘要 · Abstract (English)
Mobile systems will have to support multiple AI-based applications, each leveraging heterogeneous data sources through DNN architectures collaboratively executed within the network. To minimize the cost of the AI inference task subject to requirements on latency, quality, and - crucially - reliability of the inference process, it is vital to optimize (i) the set of sensors/data sources and (ii) the DNN architecture, (iii) the network nodes executing sections of the DNN, and (iv) the resources to use. To this end, we leverage dynamic gated neural networks with branches, and propose a novel algorithmic strategy called Quantile-constrained Inference (QIC), based upon quantile-Constrained policy optimization. QIC makes joint, high-quality, swift decisions on all the above aspects of the system, with the aim to minimize inference energy cost. We remark that this is the first contribution connecting gated dynamic DNNs with infrastructure-level decision making. We evaluate QIC using a dynamic gated DNN with stems and branches for optimal sensor fusion and inference, trained on the RADIATE dataset offering Radar, LiDAR, and Camera data, and real-world wireless measurements. Our results confirm that QIC matches the optimum and outperforms its alternatives by over 80%.
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。