# Clustered Embedding Learning for Recommender Systems

arXiv: https://arxiv.org/abs/2302.01478 · HTML: https://mlsanity.com/paper/2302.01478/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 17 of 17)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [Quantization Networks](https://mlsanity.com/paper/1911.09464/) (2019)
- [Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems](https://mlsanity.com/paper/1909.11810/) (2019)
- [On Identifiability of Nonnegative Matrix Factorization](https://mlsanity.com/paper/1709.00614/) (2017)
- [Learning to Hash with Graph Neural Networks for Recommender Systems](https://mlsanity.com/paper/2003.01917/) (2020)
- [Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer](https://mlsanity.com/paper/2108.11513/) (2021)
- [Binary Code based Hash Embedding for Web-scale Applications](https://mlsanity.com/paper/2109.02471/) (2021)
- [Learning From Hidden Traits: Joint Factor Analysis and Latent Clustering](https://mlsanity.com/paper/1605.06711/) (2016)
- [A comparative study of divisive hierarchical clustering algorithms](https://mlsanity.com/paper/1506.08977/) (2015)
- [eTREE: Learning Tree-structured Embeddings](https://mlsanity.com/paper/2012.10853/) (2020)

## Built on by (most cited first, 8 of 8)

- [Experimental Analysis of Large-scale Learnable Vector Storage Compression](https://mlsanity.com/paper/2311.15578/) (2023)
- [You Are What You Bought: Generating Customer Personas for E-commerce Applications](https://mlsanity.com/paper/2504.17304/) (2025)
- [Proxy-based Item Representation for Attribute and Context-aware Recommendation](https://mlsanity.com/paper/2312.06145/) (2023)
- [On-device Content-based Recommendation with Single-shot Embedding Pruning: A Cooperative Game Perspective](https://mlsanity.com/paper/2411.13052/) (2024)
- [Residual Multi-Task Learner for Applied Ranking](https://mlsanity.com/paper/2411.09705/) (2024)
- [Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2505.04339/) (2025)
- [DimGrow: Memory-Efficient Field-level Embedding Dimension Search](https://mlsanity.com/paper/2505.12683/) (2025)
- [Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems](https://mlsanity.com/paper/2604.18351/) (2026)

## Abstract (arXiv)

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.