Search papers, labs, and topics across Lattice.
The paper introduces a news recommendation framework that models user preferences from both global (long-term) and local temporal (short-term) perspectives to capture the evolving nature of user interests. It uses a global preference modeling component to extract long-term collaborative signals and a local preference modeling component that partitions interactions into stage-wise temporal subgraphs. The local component employs an LSTM to model progressive interest evolution and self-attention to capture long-range temporal dependencies. Experiments on real-world datasets demonstrate improved performance compared to existing methods.
News recommendations get a boost by modeling user interests as a stage-wise evolution, capturing both long-term preferences and rapidly shifting short-term interests.
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.
