# DyMRL: Dynamic Multispace Representation Learning for Multimodal Event Forecasting in Knowledge Graph Source: [DyMRL: Dynamic Multispace Representation Learning for Multimodal Event Forecasting in Knowledge Graph]() Collection index: [llms.txt]() Data updated: 2026-03-28T05:00:04.914Z Authors: Feng Zhao, Kangzheng Liu, Teng Peng, Yu Yang, Guandong Xu Published: 2026-03-25T09:45:16.000Z ## Abstract Accurate representation of multimodal knowledge is crucial for event forecasting in real-world scenarios. However, existing studies have largely focused on static settings, overlooking the dynamic acquisition and fusion of multimodal knowledge. 1) At the knowledge acquisition level, how to learn time-sensitive information of different modalities, especially the dynamic structural modality. Existing dynamic learning methods are often limited to shallow structures across heterogeneous spaces or simple unispaces, making it difficult to capture deep relation-aware geometric features. 2) At the knowledge fusion level, how to learn evolving multimodal fusion features. Existing knowledge fusion methods based on static coattention struggle to capture the varying historical contributions of different modalities to future events. To this end, we propose DyMRL, a Dynamic Multispace Representation Learning approach to efficiently acquire and fuse multimodal temporal knowledge. 1) For the former issue, DyMRL integrates time-specific structural features from Euclidean, hyperbolic, and complex spaces into a relational message-passing framework to learn deep representations, reflecting human intelligences in associative thinking, high-order abstracting, and logical reasoning. Pretrained models endow DyMRL with time-sensitive visual and linguistic intelligences. 2) For the latter concern, DyMRL incorporates advanced dual fusion-evolution attention mechanisms that assign dynamic learning emphases equally to different modalities at different timestamps in a symmetric manner. To evaluate DyMRL's event forecasting performance through leveraging its learned multimodal temporal knowledge in history, we construct four multimodal temporal knowledge graph benchmarks. Extensive experiments demonstrate that DyMRL outperforms state-of-the-art dynamic unimodal and static multimodal baseline methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multimodal Event Forecasting on GDELT IMG-TXT](): Multimodal Event Forecasting; GDELT IMG-TXT; MRR: 79.34. - [Multimodal Event Forecasting on ICE IMG-TXT 14](): Multimodal Event Forecasting; ICE IMG-TXT 14; MRR: 62.84. - [Multimodal Event Forecasting on ICE IMG-TXT 18](): Multimodal Event Forecasting; ICE IMG-TXT 18; MRR: 64.56. ## Original sources and implementation [Original paper]() [PDF]()