Federated learning (FL) is a machine learning technique that enables participants to collaboratively train high-quality models without exchanging their private data. Participants utilizing cross-silo FL (CS-FL) settings are independent organizations with different task needs, and they are concerned not only with data privacy but also with independently training their unique models due to intellectual property considerations. Most existing FL methods are incapable of satisfying the above scenarios. In this study, we present a novel FL method CoFED based on unlabeled data pseudolabeling via a process known as cotraining, which meets the needs of heterogeneous models, tasks and training processes in CS-FL. Experimental results suggest that the proposed method outperforms competing methods. This is especially true for non-independent and identically distributed (non-IID) settings and heterogeneous models, where the proposed method achieves a 35% performance improvement.