Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning

Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep methods, high-order methods, and multi-particle dynamical systems. The precision of the solution to ODEs significantly affects parameter optimization, thereby impacting model performance. In this work, we present a series of advanced explorations of Transformer architecture design to minimize the error compared to the true «solution.» First, we introduce a predictor-corrector learning framework to minimize truncation errors, which consist of a high-order predictor and a multistep corrector. Second, we propose an exponential moving average-based coefficient learning method to further strengthen our higher-order predictor. Extensive experiments on large-scale machine translation, abstractive summarization, language modeling, and natural language understanding benchmarks demonstrate the superiority of our approach. On the WMT’14 English-German and English-French tasks, our model achieved BLEU scores of 30.95 and 44.27, respectively. Additionally, on the OPUS multilingual machine translation task, our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only one-third of the parameters.