Network alignment is the task of identifying topologically and semantically similar node pairs that represent the same identity. This problem plays an important role in various application domains ranging from social network analysis to bioinformatic network interactions. However, existing alignment models either cannot handle large-scale graphs or fail to leverage different types of network information or modalities. In this paper, we propose a novel end-to-end alignment framework that can leverage different modalities to compare and align network nodes in an efficient way. More precisely, in order to exploit the richness of the network context, our model constructs multiple embeddings for each node, each of which captures one modality or type of network information. We then design a late-fusion mechanism to combine the learned embeddings based on the importance of the underlying information. Our fusion mechanism allows our model to be adapted to various type of structures of the input network. Experimental results show that our technique outperforms state-of-the-art approaches in terms of accuracy on real and synthetic datasets, while being robust against various noise factors.