TGT: A Temporal Gating Transformer for Smartphone App Usage Prediction

TL;DR

TGT introduces a novel temporal gating transformer that adaptively models daily usage rhythms, significantly improving smartphone app usage prediction accuracy, especially in cold-start scenarios, and providing interpretable insights into user behavior.

Contribution

The paper presents TGT, a transformer with a temporal gating module that enhances time-awareness and interpretability in app usage prediction, outperforming existing methods.

Findings

TGT achieves superior accuracy on real-world datasets.

It maintains robustness in cold-start scenarios.

Gating vectors reveal human-like daily usage patterns.

Abstract

Accurately predicting smartphone app usage is challenging due to the sparsity and irregularity of user behavior, especially under cold-start and low-activity conditions. Existing approaches mostly rely on static or attention-only architectures, which struggle to model fine-grained temporal dynamics. We propose TGT, a Transformer framework equipped with a temporal gating module that conditions hidden representations on the hour-of-day. Unlike conventional time embeddings, temporal gating adaptively rescales feature dimensions in a time-aware manner, working orthogonally to self-attention and strengthening temporal sensitivity. TGT further incorporates a context-aware encoder that integrates session sequences and user profiles into a unified representation. Experiments on two real-world datasets, Tsinghua App Usage and LSApp, demonstrate that TGT significantly outperforms 15 competitive baselines, achieving notable gains in HR@1 and maintaining robustness under cold-start scenarios. Beyond accuracy, analysis of gating vectors uncovers interpretable daily usage rhythms, showing that TGT learns human-consistent patterns of app behavior. These results establish TGT as both a powerful and interpretable framework for time-aware app usage prediction.