The advent of personalized news recommendation has given rise to increasingly complex recommender architectures. Most neural news recommenders rely on user click behavior and typically introduce dedicated user encoders that aggregate the content of clicked news into user embeddings (early fusion). These models are predominantly trained with standard point-wise classification objectives. The existing body of work exhibits two main shortcomings: (1) despite general design homogeneity, direct comparisons between models are hindered by varying evaluation datasets and protocols; (2) it leaves alternative model designs and training objectives vastly unexplored. In this work, we present a unified framework for news recommendation, allowing for a systematic and fair comparison of news recommenders across several crucial design dimensions: (i) candidate-awareness in user modeling, (ii) click behavior fusion, and (iii) training objectives. Our findings challenge the status quo in neural news recommendation. We show that replacing sizable user encoders with parameter-efficient dot products between candidate and clicked news embeddings (late fusion) often yields substantial performance gains. Moreover, our results render contrastive training a viable alternative to point-wise classification objectives.
翻译:个性化新闻推荐的出现催生了越来越复杂的推荐架构。大多数神经新闻推荐器依靠用户点击行为,通常引入专门的用户编码器来聚合点击新闻的内容为用户嵌入(早期融合)。这些模型主要使用标准的点形分类目标进行训练。现有的工作存在两个主要缺点:(1)尽管设计普遍相同,但直接比较各个模型受到不同的评估数据集和协议的阻碍;(2)其他模型设计和训练目标的研究仍然十分有限。
在这项工作中,我们提出了一个统一的新闻推荐框架,允许在几个关键设计维度上对新闻推荐器进行系统和公正的比较:(i)用户建模中的候选者感知能力,(ii)点击行为融合,以及(iii)训练目标。我们的研究结果挑战了神经新闻推荐的现状。我们表明,用候选新闻嵌入和点击新闻嵌入之间参数有效的点积替换相当大的用户编码器(晚期融合)通常会显著提高性能。此外,我们的研究结果表明对比训练是点形分类目标的一种可行替代方案。