Recent years have witnessed the great successes of embedding-based methods in recommender systems. Despite their decent performance, we argue one potential limitation of these methods -- the embedding magnitude has not been explicitly modulated, which may aggravate popularity bias and training instability, hindering the model from making a good recommendation. It motivates us to leverage the embedding normalization in recommendation. By normalizing user/item embeddings to a specific value, we empirically observe impressive performance gains (9\% on average) on four real-world datasets. Although encouraging, we also reveal a serious limitation when applying normalization in recommendation -- the performance is highly sensitive to the choice of the temperature $\tau$ which controls the scale of the normalized embeddings. To fully foster the merits of the normalization while circumvent its limitation, this work studied on how to adaptively set the proper $\tau$. Towards this end, we first make a comprehensive analyses of $\tau$ to fully understand its role on recommendation. We then accordingly develop an adaptive fine-grained strategy Adap-$\tau$ for the temperature with satisfying four desirable properties including adaptivity, personalized, efficiency and model-agnostic. Extensive experiments have been conducted to validate the effectiveness of the proposal. The code is available at \url{https://github.com/junkangwu/Adap_tau}.

翻译：近年来，基于嵌入的方法在推荐系统中取得了巨大成功。尽管这些方法表现出色，但我们认为其存在一个潜在局限——嵌入幅度未被显式调节，这可能加剧流行度偏差和训练不稳定性，阻碍模型做出优质推荐。这促使我们探索在推荐中应用嵌入归一化。通过将用户/物品嵌入归一化至特定数值，我们在四个真实数据集上观察到令人振奋的性能提升（平均9%）。尽管这一结果令人鼓舞，但我们同时揭示了在推荐中应用归一化时的一个严重局限——性能对控制归一化嵌入尺度的温度参数$\tau$的选择高度敏感。为充分发挥归一化优势并规避其缺陷，本研究聚焦于如何自适应设定合适$\tau$值。为此，我们首先对$\tau$进行综合分析以充分理解其在推荐中的作用机制，继而据此提出一种自适应细粒度策略Adap-$\tau$，该策略具备自适应、个性化、高效性和模型无关性四项理想特性。通过大量实验验证了该方法的有效性。代码已开源至\url{https://github.com/junkangwu/Adap_tau}。