# Modeling Stage-wise Evolution of User Interests for News Recommendation

arXiv: https://arxiv.org/abs/2603.10471 · HTML: https://mlsanity.com/paper/2603.10471/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 57 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [DKN: Deep Knowledge-Aware Network for News Recommendation](https://mlsanity.com/paper/1801.08284/) (2018)
- [Neural News Recommendation with Attentive Multi-View Learning](https://mlsanity.com/paper/1907.05576/) (2019)
- [Dynamic Graph Neural Networks for Sequential Recommendation](https://mlsanity.com/paper/2104.07368/) (2021)
- [Interest-aware Message-Passing GCN for Recommendation](https://mlsanity.com/paper/2102.10044/) (2021)
- [HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation](https://mlsanity.com/paper/2106.04408/) (2021)
- [Graph Enhanced Representation Learning for News Recommendation](https://mlsanity.com/paper/2003.14292/) (2020)
- [FeedRec: News Feed Recommendation with Various User Feedbacks](https://mlsanity.com/paper/2102.04903/) (2021)
- [News Recommendation with Candidate-aware User Modeling](https://mlsanity.com/paper/2204.04726/) (2022)
- [Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias](https://mlsanity.com/paper/2405.20718/) (2024)
- [Neural News Recommendation with Collaborative News Encoding and Structural User Encoding](https://mlsanity.com/paper/2109.00750/) (2021)
- [DIGAT: Modeling News Recommendation with Dual-Graph Interaction](https://mlsanity.com/paper/2210.05196/) (2022)
- [Two Birds with One Stone: Unified Model Learning for Both Recall and Ranking in News Recommendation](https://mlsanity.com/paper/2104.07404/) (2021)
- [Graph-Structured Driven Dual Adaptation for Mitigating Popularity Bias](https://mlsanity.com/paper/2503.23358/) (2025)
- [Mitigating Recommendation Biases via Group-Alignment and Global-Uniformity in Representation Learning](https://mlsanity.com/paper/2511.13041/) (2025)
- [CROWN: A Novel Approach to Comprehending Users' Preferences for Accurate Personalized News Recommendation](https://mlsanity.com/paper/2310.09401/) (2023)
- [RMBRec: Robust Multi-Behavior Recommendation towards Target Behaviors](https://mlsanity.com/paper/2601.08705/) (2026)

## Abstract (arXiv)

Personalized news recommendation is highly time-sensitive, as user interests are often driven by emerging events, trending topics, and shifting real-world contexts. These dynamics make it essential to model not only users' long-term preferences, which reflect stable reading habits and high-order collaborative patterns, but also their short-term, context-dependent interests that change rapidly over time. However, most existing approaches rely on a single static interaction graph, which struggles to capture both long-term preference patterns and short-term interest changes as user behavior evolves. To address this challenge, we propose a unified framework that learns user preferences from both global and local temporal perspectives. A global preference modeling component captures long-term collaborative signals from the overall interaction graph, while a local preference modeling component partitions historical interactions into stage-wise temporal subgraphs to represent short-term dynamics. Within this module, an LSTM branch models the progressive evolution of recent interests, and a self-attention branch captures long-range temporal dependencies. Extensive experiments on two large-scale real-world datasets show that our approach consistently outperforms strong baselines and delivers fresher and more relevant recommendations across diverse user behaviors and temporal settings.