Embedding tables are used by machine learning systems to work with categorical features. In modern Recommendation Systems, these tables can be very large, necessitating the development of new methods for fitting them in memory, even during training. We suggest Clustered Compositional Embeddings (CCE) which combines clustering-based compression like quantization to codebooks with dynamic methods like The Hashing Trick and Compositional Embeddings (Shi et al., 2020). Experimentally CCE achieves the best of both worlds: The high compression rate of codebook-based quantization, but *dynamically* like hashing-based methods, so it can be used during training. Theoretically, we prove that CCE is guaranteed to converge to the optimal codebook and give a tight bound for the number of iterations required.

翻译：机器学习系统使用嵌入表处理类别型特征。在现代推荐系统中，这些表可能非常庞大，因此需要开发新方法将其存储在内存中，即使在训练阶段也是如此。我们提出聚类组合嵌入（CCE），该方法将基于聚类的压缩技术（如量化到码本）与动态方法（如哈希技巧和组合嵌入，Shi 等人，2020）相结合。实验表明，CCE同时具备两者的优势：码本量化的高压缩率，以及基于哈希方法的动态特性，使其可在训练中直接使用。理论上，我们证明CCE能保证收敛到最优码本，并给出所需迭代次数的紧界。