# OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction

arXiv: https://arxiv.org/abs/2208.04482 · HTML: https://mlsanity.com/paper/2208.04482/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2022.

## Built on by (most cited first, 14 of 14)

- [One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data](https://mlsanity.com/paper/2302.06375/) (2023)
- [Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction](https://mlsanity.com/paper/2212.05735/) (2022)
- [MvFS: Multi-view Feature Selection for Recommender System](https://mlsanity.com/paper/2309.02064/) (2023)
- [OptDist: Learning Optimal Distribution for Customer Lifetime Value Prediction](https://mlsanity.com/paper/2408.08585/) (2024)
- [Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System](https://mlsanity.com/paper/2308.07760/) (2023)
- [CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models](https://mlsanity.com/paper/2312.03256/) (2023)
- [A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems](https://mlsanity.com/paper/2406.17335/) (2024)
- [Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models](https://mlsanity.com/paper/2411.15731/) (2024)
- [Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network](https://mlsanity.com/paper/2310.15342/) (2023)
- [On-device Content-based Recommendation with Single-shot Embedding Pruning: A Cooperative Game Perspective](https://mlsanity.com/paper/2411.13052/) (2024)
- [Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems](https://mlsanity.com/paper/2401.04408/) (2024)
- [ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation System](https://mlsanity.com/paper/2402.04032/) (2024)
- [Coarse-to-Fine Lightweight Meta-Embedding for ID-Based Recommendation](https://mlsanity.com/paper/2501.11870/) (2025)
- [DimGrow: Memory-Efficient Field-level Embedding Dimension Search](https://mlsanity.com/paper/2505.12683/) (2025)

## Abstract (arXiv)

Learning embedding table plays a fundamental role in Click-through rate(CTR) prediction from the view of the model performance and memory usage. The embedding table is a two-dimensional tensor, with its axes indicating the number of feature values and the embedding dimension, respectively. To learn an efficient and effective embedding table, recent works either assign various embedding dimensions for feature fields and reduce the number of embeddings respectively or mask the embedding table parameters. However, all these existing works cannot get an optimal embedding table. On the one hand, various embedding dimensions still require a large amount of memory due to the vast number of features in the dataset. On the other hand, decreasing the number of embeddings usually suffers from performance degradation, which is intolerable in CTR prediction. Finally, pruning embedding parameters will lead to a sparse embedding table, which is hard to be deployed. To this end, we propose an optimal embedding table learning framework OptEmbed, which provides a practical and general method to find an optimal embedding table for various base CTR models. Specifically, we propose pruning the redundant embeddings regarding corresponding features' importance by learnable pruning thresholds. Furthermore, we consider assigning various embedding dimensions as one single candidate architecture. To efficiently search the optimal embedding dimensions, we design a uniform embedding dimension sampling scheme to equally train all candidate architectures, meaning architecture-related parameters and learnable thresholds are trained simultaneously in one supernet. We then propose an evolution search method based on the supernet to find the optimal embedding dimensions for each field. Experiments on public datasets show that OptEmbed can learn a compact embedding table which can further improve the model performance.