Although deep learning has gained popularity in the field of fault diagnosis, its limitations are also equally apparent, including: (1) heavy reliance on a substantial volume of labeled samples; (2) a lack of interpretability. To confront these issues, this article proposes a novel interpretable semi-supervised graph learning model for intelligent fault diagnosis of hydraulic pumps. A comparison between the raw data and the model's hidden layer representations is conducted to minimize feature loss. The model commences by preliminarily learning fault information that is intermixed with noise, leveraging a substantial corpus of unlabeled data. In response to the intricacy of downstream tasks, an interpretable feature reconstruction module is introduced. This module employs a nonlinear surrogate model to fit and elucidate the learned features, embedding the explanation scores into the features to reconstruct the samples, a process utilized for model fine-tuning. The feature reconstruction module capitalizes on the explanatory power of the surrogate model, guiding the model to concentrate more on features with significant impact. This method not only provides interpretability during model training but also expedites the convergence speed of the model. Finally, two hydraulic pump experiment cases are used to verify the effectiveness of the model, and the results show that our method has obvious advantages in reducing label dependence and increasing model reliability for decision making.