# Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems

arXiv: https://arxiv.org/abs/2604.18351 · HTML: https://mlsanity.com/paper/2604.18351/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 72 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 28 of 28)

- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [The Architectural Implications of Facebook's DNN-based Personalized Recommendation](https://mlsanity.com/paper/1906.03109/) (2019)
- [Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems](https://mlsanity.com/paper/1909.02107/) (2019)
- [TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models](https://mlsanity.com/paper/2101.11714/) (2021)
- [Towards Representation Alignment and Uniformity in Collaborative Filtering](https://mlsanity.com/paper/2206.12811/) (2022)
- [Hash Embeddings for Efficient Word Representations](https://mlsanity.com/paper/1709.03933/) (2017)
- [Learning to Embed Categorical Features without Embedding Tables for Recommendation](https://mlsanity.com/paper/2010.10784/) (2020)
- [Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems](https://mlsanity.com/paper/2007.14523/) (2020)
- [Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems](https://mlsanity.com/paper/2002.08530/) (2020)
- [On-Device Next-Item Recommendation with Self-Supervised Knowledge Distillation](https://mlsanity.com/paper/2204.11091/) (2022)
- [Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems](https://mlsanity.com/paper/2305.12102/) (2023)
- [Embedding Compression in Recommender Systems: A Survey](https://mlsanity.com/paper/2408.02304/) (2024)
- [ScaleFreeCTR: MixCache-based Distributed Training System for CTR Models with Huge Embedding Table](https://mlsanity.com/paper/2104.08542/) (2021)
- [Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations](https://mlsanity.com/paper/1806.09464/) (2018)
- [Efficient High-Quality Clustering for Large Bipartite Graphs](https://mlsanity.com/paper/2312.16926/) (2023)
- [Clustered Embedding Learning for Recommender Systems](https://mlsanity.com/paper/2302.01478/) (2023)
- [Efficiently inferring community structure in bipartite networks](https://mlsanity.com/paper/1403.2933/) (2014)
- [Saec: Similarity-Aware Embedding Compression in Recommendation Systems](https://mlsanity.com/paper/1903.00103/) (2019)
- [Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation](https://mlsanity.com/paper/2105.14068/) (2021)
- [Effective Clustering on Large Attributed Bipartite Graphs](https://mlsanity.com/paper/2405.11922/) (2024)
- [Community Detection in Bipartite Networks with Stochastic Blockmodels](https://mlsanity.com/paper/2001.11818/) (2020)
- [Explaining reviews and ratings with PACO: Poisson Additive Co-Clustering](https://mlsanity.com/paper/1512.01845/) (2015)
- [Lightweight Embeddings for Graph Collaborative Filtering](https://mlsanity.com/paper/2403.18479/) (2024)
- [GraphHash: Graph Clustering Enables Parameter Efficiency in Recommender Systems](https://mlsanity.com/paper/2412.17245/) (2024)
- [The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems](https://mlsanity.com/paper/2505.11388/) (2025)
- [Clustering the Sketch: A Novel Approach to Embedding Table Compression](https://mlsanity.com/paper/2210.05974/) (2022)

## Abstract (arXiv)

Recommender systems have advanced markedly over the past decade by transforming each user/item into a dense embedding vector with deep learning models. At industrial scale, embedding tables constituted by such vectors of all users/items demand a vast amount of parameters and impose heavy compute and memory overhead during training and inference, hindering model deployment under resource constraints. Existing solutions towards embedding compression either suffer from severely compromised recommendation accuracy or incur considerable computational costs. To mitigate these issues, this paper presents BACO, a fast and effective framework for compressing embedding tables. Unlike traditional ID hashing, BACO is built on the idea of exploiting collaborative signals in user-item interactions for user and item groupings, such that similar users/items share the same embeddings in the codebook. Specifically, we formulate a balanced co-clustering objective that maximizes intra-cluster connectivity while enforcing cluster-volume balance, and unify canonical graph clustering techniques into the framework through rigorous theoretical analyses. To produce effective groupings while averting codebook collapse, BACO instantiates this framework with a principled weighting scheme for users and items, an efficient label propagation solver, as well as secondary user clusters. Our extensive experiments comparing BACO against full models and 18 baselines over benchmark datasets demonstrate that BACO cuts embedding parameters by over 75% with a drop of at most 1.85% in recall, while surpassing the strongest baselines by being up to 346X faster.