Predicting gastric cancer disease-free survival (DFS) and identifying patients probably with high risk are imperative for more appropriate clinical treatment plans. Compared with CT-based radiomics researches adopting linear Cox proportional hazards models, deep neural networks can perform nonlinear transformations and investigate complex associations of image features with prognosis. Exploring shared information between post-contrast CT (with better visual enhancement) and pre-contrast CT (with few side effects and contraindications) is another challenge. In this work, a cross-phase adversarial domain adaptation (CPADA) framework is proposed to adapt a deep DFS prediction network (DDFS-Net) from arterial phase to pre-contrast phase. The DDFS-Net is designed for feature learning and trained by optimizing the average negative log function of Cox partial likelihood. The CPADA maps the feature space of pre-contrast phase (target) to arterial phase (source) in an adversarial manner by measuring Wasserstein distance. The proposed methods are evaluated on a dataset of 249 gastric cancer patients by concordance index, receiver operating characteristic curves, and Kaplan-Meier survival curves. The results demonstrate that our DDFS-Net outperforms linear survival analysis methods, and the CPADA works better than supervised learning and direct transfer schemes.