TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation

TL;DR

TimeMM introduces a spectral filtering framework that dynamically models evolving user preferences in multimodal recommendation systems by leveraging temporal kernels and adaptive spectral responses.

Contribution

It proposes a novel time-conditioned spectral filtering approach that captures non-stationary interests and modality-specific temporal sensitivities without explicit eigendecomposition.

Findings

TimeMM outperforms state-of-the-art methods on real-world benchmarks.

It maintains linear-time scalability.

The framework effectively models continuous preference evolution.

Abstract

Multimodal recommendation improves user modeling by integrating collaborative signals with heterogeneous item content. In real applications, user interests evolve over time and exhibit nonstationary dynamics, where different preference factors change at different rates. This challenge is amplified in multimodal settings because visual and textual cues can dominate decisions under different temporal regimes. Despite strong progress, most multimodal recommenders still rely on static interaction graphs or coarse temporal heuristics, which limits their ability to model continuous preference evolution with fine-grained temporal adaptation. To address these limitations, we propose TimeMM, a time-conditioned spectral filtering framework for dynamic multimodal recommendation. TimeMM instantiates Time-as-Operator by mapping interaction recency to a family of parametric temporal kernels that reweight edges on the user--item graph, producing component-specific representations without explicit eigendecomposition. To capture non-stationary interests, we introduce Adaptive Spectral Filtering that mixes the operator bank according to temporal context, yielding prediction-specific effective spectral responses. To account for modality-specific temporal sensitivity, we further propose Spectral-Aware Modality Routing that calibrates visual and textual contributions conditioned on the same temporal context. Finally, a ranking-space Spectral Diversity Regularization encourages complementary expert behaviors and prevents filter-bank collapse. Extensive experiments on real-world benchmarks demonstrate that TimeMM consistently outperforms state-of-the-art multimodal recommenders while maintaining linear-time scalability.