论文标题
通过连续聚类和机器学习的因素图的结构优化用于符号检测
Structural Optimization of Factor Graphs for Symbol Detection via Continuous Clustering and Machine Learning
论文作者
论文摘要
我们提出了一种新方法，以优化基于图的推理的因子图的结构。作为推理任务，我们考虑在线性符号间干扰通道上的符号检测。因子图框架有可能产生低复杂性符号探测器。然而，循环因子图上的总和产物算法是次优的，其性能对基础图高度敏感。因此，我们使用机器学习以端到端方式优化了基础因子图的结构。为此，我们将结构优化转变为低度因子节点的聚类问题，该问题将已知的通道模型纳入优化。此外，我们研究了这种方法与神经信念传播的组合，从而为特定通道产生了接近最大的后验符号检测性能。
We propose a novel method to optimize the structure of factor graphs for graph-based inference. As an example inference task, we consider symbol detection on linear inter-symbol interference channels. The factor graph framework has the potential to yield low-complexity symbol detectors. However, the sum-product algorithm on cyclic factor graphs is suboptimal and its performance is highly sensitive to the underlying graph. Therefore, we optimize the structure of the underlying factor graphs in an end-to-end manner using machine learning. For that purpose, we transform the structural optimization into a clustering problem of low-degree factor nodes that incorporates the known channel model into the optimization. Furthermore, we study the combination of this approach with neural belief propagation, yielding near-maximum a posteriori symbol detection performance for specific channels.
