Recently, research on the classification for inverse synthetic aperture radar (ISAR) images continues to deepen. However, the maneuvering and attitude adjustment of space targets will bring high-order terms to received echoes, which causes defocus on ISAR images and affects the classification. The current classification models ignore the information of high-order terms containing in the relationship of real parts and imaginary parts of data. To this end, this letter proposes an end-to-end framework, called complex-valued (CV)-graph neural network (GNN), specifically for the classification of defocused ISAR images under the few-shot condition. It models the features of real parts and imaginary parts of CV images as graph information reasoning. Specifically, the deep relationship between them is mined to contribute to classification by CV graph convolution. Moreover, the backpropagation process is derived in detail for updating the weights and bias of the network. The proposed method is then experimented with a mixed few-shot dataset of real and simulated data. Compared with the state-of-the-art methods, CV-GNN performs well in defocused image classification for each class of targets, and ablation studies verify the effectiveness of CV network and GNN. The code and dataset will be available online (https://github.com/yhx-hit/cv_gnn).