In this paper, we introduce a new nonlinear optical channel equalizer based on Transformers. By leveraging parallel computation and attending directly to the memory across a sequence of symbols, we show that Transformers can be used effectively for nonlinear equalization in coherent long-haul transmission. For this application, we present an implementation of the encoder part of the Transformer and analyze its performance over a wide range of different hyper-parameters. It is shown that by processing blocks of symbols at each iteration and carefully selecting subsets of the encoder's output to be processed together, an efficient nonlinear compensation can be achieved for different complexity constraints. We also propose the use of a physic-informed mask inspired by nonlinear perturbation theory for reducing the computational complexity of the attention mechanism.

翻译：本文提出一种基于Transformer的新型非线性光信道均衡器。通过利用并行计算并直接关注符号序列中的记忆特征，我们证明了Transformer可有效用于相干长距离传输中的非线性均衡。针对该应用，我们实现了Transformer编码器部分，并在多种超参数配置下分析了其性能。研究表明，通过每次迭代处理符号块并精心选择编码器输出子集进行联合处理，可在不同复杂度约束下实现高效的非线性补偿。我们还提出了一种受非线性微扰理论启发的物理信息掩码，用于降低注意力机制的计算复杂度。