Certification of quantum systems is pivotal for the scalability of quantum computing, aiming to estimate the accuracy and correct functioning of quantum devices by analyzing the statistics of the data from quantum measurements. Traditional supervised methods, which rely on extensive labeled measurement outcomes, are used to infer the properties of unknown quantum systems. However, the labeling process demands computational and memory resources that increase exponentially with the number of qubits. We propose SEMIQ, manage to achieve (for the first time) semi-supervised learning for quantum system certification. SEMIQ is specialized by its network architecture specifically designed to ensure permutation invariance for unordered quantum measurements and maintain robustness in the face of measurement uncertainties. Our empirical studies cover simulations on two types of quantum systems including the Heisenberg Model and Variational Quantum Circuits (VQC) Model, with the system size up to 50 qubits. The numerical results show SEMIQ’s superiority over traditional supervised models in scenarios with limited labels.