Clustered Embedding Learning for Recommender Systems

by   Yizhou Chen, et al.

In recent years, recommender systems have advanced rapidly, where embedding learning for users and items plays a critical role. A standard method learns a unique embedding vector for each user and item. However, such a method has two important limitations in real-world applications: 1) it is hard to learn embeddings that generalize well for users and items with rare interactions on their own; and 2) it may incur unbearably high memory costs when the number of users and items scales up. Existing approaches either can only address one of the limitations or have flawed overall performances. In this paper, we propose Clustered Embedding Learning (CEL) as an integrated solution to these two problems. CEL is a plug-and-play embedding learning framework that can be combined with any differentiable feature interaction model. It is capable of achieving improved performance, especially for cold users and items, with reduced memory cost. CEL enables automatic and dynamic clustering of users and items in a top-down fashion, where clustered entities jointly learn a shared embedding. The accelerated version of CEL has an optimal time complexity, which supports efficient online updates. Theoretically, we prove the identifiability and the existence of a unique optimal number of clusters for CEL in the context of nonnegative matrix factorization. Empirically, we validate the effectiveness of CEL on three public datasets and one business dataset, showing its consistently superior performance against current state-of-the-art methods. In particular, when incorporating CEL into the business model, it brings an improvement of +0.6% in AUC, which translates into a significant revenue gain; meanwhile, the size of the embedding table gets 2650 times smaller.


page 1

page 2

page 3

page 4


Cross-Attribute Matrix Factorization Model with Shared User Embedding

Over the past few years, deep learning has firmly established its prowes...

Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System

With the continuous increase of users and items, conventional recommende...

Efficient Mixed Dimension Embeddings for Matrix Factorization

Despite the prominence of neural network approaches in the field of reco...

Collaborative Filtering with Information-Rich and Information-Sparse Entities

In this paper, we consider a popular model for collaborative filtering i...

Binary Code based Hash Embedding for Web-scale Applications

Nowadays, deep learning models are widely adopted in web-scale applicati...

AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation

In the domain of streaming recommender systems, conventional methods for...

Top-N recommendations from expressive recommender systems

Normalized nonnegative models assign probability distributions to users ...

Please sign up or login with your details

Forgot password? Click here to reset