论文标题
基于自我注意力的软性较小成本流学习的时间序列中的信号盲界
Blind Deinterleaving of Signals in Time Series with Self-attention Based Soft Min-cost Flow Learning
论文作者
论文摘要
我们提出了一种端到端的学习方法，以解决时间序列中的模式的去介绍，尤其是雷达信号。一旦存在适当的成本，我们将信号聚类问题与最小成本流程联系起来。我们制定了一个涉及Min-Cost流量的双层优化问题，作为从监督培训数据中学习此类费用的子问题。然后，我们通过基于自我注意力的神经网络近似较低的优化问题，并提供一个可训练的框架，该框架将输入中的模式作为不同的流动。我们通过在一个大型数据集上进行的大量实验评估我们的方法，并具有几个具有挑战性的方案以显示效率。
We propose an end-to-end learning approach to address deinterleaving of patterns in time series, in particular, radar signals. We link signal clustering problem to min-cost flow as an equivalent problem once the proper costs exist. We formulate a bi-level optimization problem involving min-cost flow as a sub-problem to learn such costs from the supervised training data. We then approximate the lower level optimization problem by self-attention based neural networks and provide a trainable framework that clusters the patterns in the input as the distinct flows. We evaluate our method with extensive experiments on a large dataset with several challenging scenarios to show the efficiency.
