FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
This addresses multimodal fusion challenges in critical fields, but appears incremental as it builds on existing mixture-of-experts methods.
The paper tackles the problem of handling multimodal data with missing elements and irregular sampling by introducing FuseMoE, a mixture-of-experts framework with a novel gating function, which improves convergence rates and performance in downstream tasks.
As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and sparsity of collected samples. Successfully leveraging this complex data, while overcoming the scarcity of high-quality training samples, is key to improving these models' predictive performance. We introduce ``FuseMoE'', a mixture-of-experts framework incorporated with an innovative gating function. Designed to integrate a diverse number of modalities, FuseMoE is effective in managing scenarios with missing modalities and irregularly sampled data trajectories. Theoretically, our unique gating function contributes to enhanced convergence rates, leading to better performance in multiple downstream tasks. The practical utility of FuseMoE in the real world is validated by a diverse set of challenging prediction tasks.