Graph fusion is a widely adopted approach to multimodality fusion for image content analysis and retrieval. Typical graph fusion methods take into account both intra-graph relationship and inter-graph relationship of images in the fusion process. Although intra-graph relationship can be built easily based on the similarities of images in each modality, it is not trivial to build the inter-graph relationship. In this paper, a novel method is proposed to construct the inter-graph relationship of images by introducing virtual links and setting the link weights to one. This scheme makes the iterative fusion process more efficient and effective. Experimental results on a public image dataset show that the proposed method outperforms the general similarity graph methods in image clustering and retrieval.