用层叠理论提升多模态设备协作，让不同能力的终端更聪明地协同工作。

In large-scale communication systems, increasingly complex scenarios require more intelligent collaboration among edge devices collecting various multimodal sensory data to achieve a more comprehensive understanding of the environment and improve decision-making accuracy. However, conventional federated learning (FL) algorithms typically consider unimodal datasets, require identical model architectures, and fail to leverage the rich information embedded in multimodal data, limiting their applicability to real-world scenarios with diverse modalities and varying client capabilities. To address this issue, we propose Sheaf-DMFL, a novel decentralized multimodal learning framework leveraging sheaf theory to enhance collaboration among devices with diverse modalities. Specifically, each client has a set of local feature encoders for its different modalities, whose outputs are concatenated before passing through a task-specific layer. While encoders for the same modality are trained collaboratively across clients, we capture the intrinsic correlations among clients' task-specific layers using a sheaf-based structure. To further enhance learning capability, we propose an enhanced algorithm named Sheaf-DMFL-Att, which tailors the attention mechanism within each client to capture correlations among different modalities. A rigorous convergence analysis of Sheaf-DMFL-Att is provided, establishing its theoretical guarantees. Extensive simulations are conducted on real-world link blockage prediction and mmWave beamforming scenarios, demonstrate the superiority of the proposed algorithms in such heterogeneous wireless communication systems.