Popularity bias is a widespread problem in the field of recommender systems, where popular items tend to dominate recommendation results. In this work, we propose 'Test Time Embedding Normalization' as a simple yet effective strategy for mitigating popularity bias, which surpasses the performance of the previous mitigation approaches by a significant margin. Our approach utilizes the normalized item embedding during the inference stage to control the influence of embedding magnitude, which is highly correlated with item popularity. Through extensive experiments, we show that our method combined with the sampled softmax loss effectively reduces popularity bias compare to previous approaches for bias mitigation. We further investigate the relationship between user and item embeddings and find that the angular similarity between embeddings distinguishes preferable and non-preferable items regardless of their popularity. The analysis explains the mechanism behind the success of our approach in eliminating the impact of popularity bias. Our code is available at https://github.com/ml-postech/TTEN.

翻译：流行度偏差是推荐系统领域中的普遍问题，热门物品往往主导推荐结果。本文提出“测试时嵌入归一化”策略，以简洁有效的方式缓解流行度偏差，其性能显著超越以往缓解方法。该方法在推理阶段利用归一化后的物品嵌入，有效控制与物品流行度高度相关的嵌入模长影响。通过大量实验表明，与先前的偏差缓解方法相比，将本方法与采样软最大损失相结合，能更有效地降低流行度偏差。我们进一步探究用户嵌入与物品嵌入的关系，发现无论物品流行度如何，嵌入之间的角度相似性可区分偏好与非偏好物品。该分析揭示了本方法消除流行度偏差影响的内在机制。代码已开源至 https://github.com/ml-postech/TTEN。