Large pretrained language models (PLM) have become de facto news encoders in modern news recommender systems, due to their strong ability in comprehending textual content. These huge Transformer-based architectures, when finetuned on recommendation tasks, can greatly improve news recommendation performance. However, the PLM-based pretrain-finetune framework incurs high computational cost and energy consumption, primarily due to the extensive redundant processing of news encoding during each training epoch. In this paper, we propose the ``Only Encode Once'' framework for news recommendation (OLEO), by decoupling news representation learning from downstream recommendation task learning. The decoupled design makes content-based news recommender as green and efficient as id-based ones, leading to great reduction in computational cost and training resources. Extensive experiments show that our OLEO framework can reduce carbon emissions by up to 13 times compared with the state-of-the-art pretrain-finetune framework and maintain a competitive or even superior performance level. The source code is released for reproducibility.

翻译：大型预训练语言模型（PLM）凭借其强大的文本内容理解能力，已成为现代新闻推荐系统中的事实标准新闻编码器。这些基于Transformer的庞大架构在推荐任务上微调后，能显著提升新闻推荐性能。然而，基于PLM的预训练-微调框架会产生高昂的计算成本和能源消耗，这主要源于每个训练周期中对新闻编码的大量冗余处理。本文提出用于新闻推荐的“仅编码一次”框架（OLEO），通过解耦新闻表示学习与下游推荐任务学习来实现。这种解耦设计使基于内容的新闻推荐系统变得与基于ID的推荐系统一样绿色高效，大幅降低了计算成本和训练资源。大量实验表明，与最先进的预训练-微调框架相比，我们的OLEO框架最多可减少13倍的碳排放，同时保持有竞争力甚至更优的性能水平。源代码已发布以确保可复现性。