Task-aware Distributed Source Coding under Dynamic Bandwidth
Task-aware Distributed Source Coding under Dynamic Bandwidth
复制标题
DOI：
10.48550/arxiv.2305.15523
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Po-han Li;S. Ankireddy;Ruihan Zhao;Hossein Nourkhiz Mahjoub;Ehsan Moradi-Pari;U. Topcu;Sandeep P. Chinchali;Hyeji Kim
中科院分区：
文献类型：
--
作者：
Po-han Li;S. Ankireddy;Ruihan Zhao;Hossein Nourkhiz Mahjoub;Ehsan Moradi-Pari;U. Topcu;Sandeep P. Chinchali;Hyeji Kim
在多传感器网络中，相关数据的有效压缩是最小化通信过载的关键。在这样的网络中，由于有限的通信带宽，每个传感器独立地压缩数据并将其传输到中心节点。中心节点的解码器解压缩数据并将其传递给预先训练的基于机器学习的任务，以生成最终输出。因此，重要的是压缩与任务相关的特征。此外，最终性能在很大程度上取决于总可用带宽。在实践中，经常会遇到不同的带宽可用性，并且更高的带宽会导致任务的更好性能。我们设计了一种由独立编码器和联合解码器组成的新型分布式压缩框架，我们称之为神经分布式主成分分析（NDPCA）。NDPCA通过单一模型将多个源的数据灵活地压缩到任何可用带宽，从而减少计算和存储开销。NDPCA通过学习低秩任务表示并在传感器之间有效地分配带宽来实现这一点，从而在性能和带宽之间提供了一个优雅的权衡。实验表明，NDPCA提高了9%的成功率的多视图机械臂操作和14%的卫星图像上的目标检测任务的准确性相比，具有均匀的带宽分配的自动编码器。
Efficient compression of correlated data is essential to minimize communication overload in multi-sensor networks. In such networks, each sensor independently compresses the data and transmits them to a central node due to limited communication bandwidth. A decoder at the central node decompresses and passes the data to a pre-trained machine learning-based task to generate the final output. Thus, it is important to compress the features that are relevant to the task. Additionally, the final performance depends heavily on the total available bandwidth. In practice, it is common to encounter varying availability in bandwidth, and higher bandwidth results in better performance of the task. We design a novel distributed compression framework composed of independent encoders and a joint decoder, which we call neural distributed principal component analysis (NDPCA). NDPCA flexibly compresses data from multiple sources to any available bandwidth with a single model, reducing computing and storage overhead. NDPCA achieves this by learning low-rank task representations and efficiently distributing bandwidth among sensors, thus providing a graceful trade-off between performance and bandwidth. Experiments show that NDPCA improves the success rate of multi-view robotic arm manipulation by 9% and the accuracy of object detection tasks on satellite imagery by 14% compared to an autoencoder with uniform bandwidth allocation.