# USE: Dynamic User Modeling with Stateful Sequence Models

arXiv: https://arxiv.org/abs/2403.13344 · HTML: https://mlsanity.com/paper/2403.13344/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Recurrent Neural Networks with Top-k Gains for Session-based Recommendations](https://mlsanity.com/paper/1706.03847/) (2017)
- [Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation](https://mlsanity.com/paper/1609.09152/) (2016)
- [Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction](https://mlsanity.com/paper/1905.09248/) (2019)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [PinnerFormer: Sequence Modeling for User Representation at Pinterest](https://mlsanity.com/paper/2205.04507/) (2022)
- [Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction](https://mlsanity.com/paper/1905.00758/) (2019)
- [Context-aware Sequential Recommendation](https://mlsanity.com/paper/1609.05787/) (2016)
- [PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision](https://mlsanity.com/paper/2010.01494/) (2020)
- [Learning Invariant Representations of Social Media Users](https://mlsanity.com/paper/1910.04979/) (2019)
- [Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation](https://mlsanity.com/paper/1607.04373/) (2016)
- [Contextual Embeddings: When Are They Worth It?](https://mlsanity.com/paper/2005.09117/) (2020)
- [General-Purpose User Embeddings based on Mobile App Usage](https://mlsanity.com/paper/2005.13303/) (2020)
- [SimCURL: Simple Contrastive User Representation Learning from Command Sequences](https://mlsanity.com/paper/2207.14760/) (2022)
- [A Reference Data Model for Process-Related User Interaction Logs](https://mlsanity.com/paper/2207.12054/) (2022)

## Built on by (most cited first, 1 of 1)

- [OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning](https://mlsanity.com/paper/2504.17811/) (2025)

## Abstract (arXiv)

User embeddings play a crucial role in user engagement forecasting and personalized services. Recent advances in sequence modeling have sparked interest in learning user embeddings from behavioral data. Yet behavior-based user embedding learning faces the unique challenge of dynamic user modeling. As users continuously interact with the apps, user embeddings should be periodically updated to account for users' recent and long-term behavior patterns. Existing methods highly rely on stateless sequence models that lack memory of historical behavior. They have to either discard historical data and use only the most recent data or reprocess the old and new data jointly. Both cases incur substantial computational overhead. To address this limitation, we introduce User Stateful Embedding (USE). USE generates user embeddings and reflects users' evolving behaviors without the need for exhaustive reprocessing by storing previous model states and revisiting them in the future. Furthermore, we introduce a novel training objective named future W-behavior prediction to transcend the limitations of next-token prediction by forecasting a broader horizon of upcoming user behaviors. By combining it with the Same User Prediction, a contrastive learning-based objective that predicts whether different segments of behavior sequences belong to the same user, we further improve the embeddings' distinctiveness and representativeness. We conducted experiments on 8 downstream tasks using Snapchat users' behavioral logs in both static (i.e., fixed user behavior sequences) and dynamic (i.e., periodically updated user behavior sequences) settings. We demonstrate USE's superior performance over established baselines. The results underscore USE's effectiveness and efficiency in integrating historical and recent user behavior sequences into user embeddings in dynamic user modeling.