# Discrete Semantic Tokenization for Deep CTR Prediction

arXiv: https://arxiv.org/abs/2403.08206 · HTML: https://mlsanity.com/paper/2403.08206/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2024.

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

- [Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning](https://mlsanity.com/paper/2405.16435/) (2024)
- [An Automatic Graph Construction Framework based on Large Language Models for Recommendation](https://mlsanity.com/paper/2412.18241/) (2024)
- [Large Language Model as Token Compressor and Decompressor](https://mlsanity.com/paper/2603.25340/) (2026)
- [A Survey on LLM-based News Recommender Systems](https://mlsanity.com/paper/2502.09797/) (2025)
- [PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation](https://mlsanity.com/paper/2508.18166/) (2025)
- [HMDN: Hierarchical Multi-Distribution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/2408.01332/) (2024)
- [LLM-driven Multimodal Recommendation](https://mlsanity.com/paper/2602.05474/) (2026)
- [Towards a Densing Law for User Representation Learning at Billion-Scale Capacity](https://mlsanity.com/paper/2608.23392/) (2026)

## Abstract (arXiv)

Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios. The content-encoding paradigm, which integrates user and item encoders directly into CTR models, prioritizes space over time. In contrast, the embedding-based paradigm transforms item and user semantics into latent embeddings, subsequently caching them to optimize processing time at the expense of space. In this paper, we introduce a new semantic-token paradigm and propose a discrete semantic tokenization approach, namely UIST, for user and item representation. UIST facilitates swift training and inference while maintaining a conservative memory footprint. Specifically, UIST quantizes dense embedding vectors into discrete tokens with shorter lengths and employs a hierarchical mixture inference module to weigh the contribution of each user--item token pair. Our experimental results on news recommendation showcase the effectiveness and efficiency (about 200-fold space compression) of UIST for CTR prediction.