Embedding learning of categorical features (e.g. user/item IDs) is at the
core of various recommendation models including matrix factorization and neural
collaborative filtering. The standard approach creates an embedding table where
each row represents a dedicated embedding vector for every unique feature
value. However, this method fails to efficiently handle high-cardinality
features and unseen feature values (e.g. new video ID) that are prevalent in
real-world recommendation systems. In this paper, we propose an alternative
embedding framework Deep Hash Embedding (DHE), replacing embedding tables by a
deep embedding network to compute embeddings on the fly. DHE first encodes the
feature value to a unique identifier vector with multiple hashing functions and
transformations, and then applies a DNN to convert the identifier vector to an
embedding. The encoding module is deterministic, non-learnable, and free of
storage, while the embedding network is updated during the training time to
learn embedding generation. Empirical results show that DHE achieves comparable
AUC against the standard one-hot full embedding, with smaller model sizes. Our
work sheds light on the design of DNN-based alternative embedding schemes for
categorical features without using embedding table lookup.

本文提出了一种名为 Deep Hash Embedding（DHE）的替代嵌入框架，通过多重哈希函数和转换将特征值编码为唯一标识符向量，并将其应用于 DNN 生成嵌入，用于处理高基数特征和未知特征值等实际推荐系统中存在的挑战。实证结果表明，DHE 在模型大小更小的情况下实现了与标准的 one-hot 全嵌入相当的 AUC，为基于 DNN 的替代嵌入方案的设计提供了新思路。