arXiv:2507.18800cs.IRcs.LG2025-07被引 9

用内容特征共享嵌入,提升音乐推荐准确率与多样性,同时缩小模型体积。

Semantic IDs for Music Recommendation

  • 用内容特征生成共享嵌入(语义ID),替代独立物品嵌入。
  • 在两个音乐推荐数据集上提升准确率与推荐多样性,模型规模减少。
  • 已在流媒体平台实测,适合资源受限场景下的推荐系统优化。

训练下一物品推荐系统通常需为每个物品学习唯一嵌入,这占用了大部分可训练参数。通过使用内容信息的共享嵌入(如语义ID),可显著减少需存储的独立嵌入数量,使模型更轻量;相应地,因内存占用降低,可增加模型复杂度。我们在两个音乐推荐数据集上验证了该方法的有效性,包括在某音乐流媒体服务上的线上A/B测试。结果表明,使用语义ID不仅能提升推荐准确率和多样性,还能显著减小模型规模。

原文摘要 · Abstract (English)

Training recommender systems for next-item recommendation often requires unique embeddings to be learned for each item, which may take up most of the trainable parameters for a model. Shared embeddings, such as using content information, can reduce the number of distinct embeddings to be stored in memory. This allows for a more lightweight model; correspondingly, model complexity can be increased due to having fewer embeddings to store in memory. We show the benefit of using shared content-based features ('semantic IDs') in improving recommendation accuracy and diversity, while reducing model size, for two music recommendation datasets, including an online A/B test on a music streaming service.

推荐系统嵌入共享音乐推荐

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。