Network coding allows distributed information sources such as sensors to efficiently compress and transmit data to distributed receivers across a bandwidth-limited network. Classical network coding is largely task-agnostic -- the coding schemes mainly aim to faithfully reconstruct data at the receivers, regardless of what ultimate task the received data is used for. In this paper, we analyze a new task-driven network coding problem, where distributed receivers pass transmitted data through machine learning (ML) tasks, which provides an opportunity to improve efficiency by transmitting salient task-relevant data representations. Specifically, we formulate a task-aware network coding problem over a butterfly network in real-coordinate space, where lossy analog compression through principal component analysis (PCA) can be applied. A lower bound for the total loss function for the formulated problem is given, and necessary and sufficient conditions for achieving this lower bound are also provided. We introduce ML algorithms to solve the problem in the general case, and our evaluation demonstrates the effectiveness of task-aware network coding.
翻译:网络编码使分布式信息源,例如传感器能够有效地压缩并传送数据到带宽限制的网络中分布式接收器。古典网络编码基本上是任务不可知性的 -- -- 编码办法的主要目的是忠实地重建接收器的数据,而不论所收到数据最终用于何种任务。在本文件中,我们分析一个新的任务驱动网络编码问题,即分布式接收器通过机器学习(ML)任务传递数据,从而提供机会通过传输与任务相关的突出数据表示来提高效率。具体地说,我们为实际坐标空间的蝴蝶网络设计了一个任务认知式网络编码问题,在那里,可以应用主要部件分析(PCA)进行损失模拟压缩。为所拟订的问题的总损失函数设定了一个较低的约束,并为达到这一较低约束提供了必要和充分的条件。我们引入了 ML 算法,以在一般情况下解决问题,我们的评价显示了任务认知式网络编码的有效性。