# Dynamic Time-aware Continual User Representation Learning

arXiv: https://arxiv.org/abs/2504.16501 · HTML: https://mlsanity.com/paper/2504.16501/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [Neural Factorization Machines for Sparse Predictive Analytics](https://mlsanity.com/paper/1708.05027/) (2017)
- [A Simple Convolutional Generative Network for Next Item Recommendation](https://mlsanity.com/paper/1808.05163/) (2018)
- [One Person, One Model, One World: Learning Continual User Representation without Forgetting](https://mlsanity.com/paper/2009.13724/) (2020)
- [Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks](https://mlsanity.com/paper/1805.10727/) (2018)
- [MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation](https://mlsanity.com/paper/2304.08382/) (2023)
- [Exploiting Behavioral Consistence for Universal User Representation](https://mlsanity.com/paper/2012.06146/) (2020)
- [Task Relation-aware Continual User Representation Learning](https://mlsanity.com/paper/2306.01792/) (2023)
- [AutoFT: Automatic Fine-Tune for Parameters Transfer Learning in Click-Through Rate Prediction](https://mlsanity.com/paper/2106.04873/) (2021)

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

- [Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback](https://mlsanity.com/paper/2602.12612/) (2026)

## Abstract (arXiv)

Traditional user modeling (UM) approaches have primarily focused on designing models for a single specific task, but they face limitations in generalization and adaptability across various tasks. Recognizing these challenges, recent studies have shifted towards continual learning (CL)-based universal user representation learning aiming to develop a single model capable of handling multiple tasks. Despite advancements, existing methods are in fact evaluated under an unrealistic scenario that does not consider the passage of time as tasks progress, which overlooks newly emerged items that may change the item distribution of previous tasks. In this paper, we introduce a practical evaluation scenario on which CL-based universal user representation learning approaches should be evaluated, which takes into account the passage of time as tasks progress. Then, we propose a novel framework Dynamic Time-aware continual user representation learner, named DITTO, designed to alleviate catastrophic forgetting despite continuous shifts in item distribution, while also allowing the knowledge acquired from previous tasks to adapt to the current shifted item distribution. Through our extensive experiments, we demonstrate the superiority of DITTO over state-of-the-art methods under a practical evaluation scenario. Our source code is available at https://github.com/seungyoon-Choi/DITTO_official.