 In this paper, the authors present a novel approach for seizure prediction using deep learning methods. They propose a simple and efficient end-to-end outer network and supervised contrastive learning, ADNET-SCL, which reduces computational complexity while maintaining accuracy. Additionally, they employ contrastive learning to effectively use label information, points of the same class are clustered together in the projection space, and points of different class are pushed apart at the same time. Furthermore, the proposed model is trained by combining the supervised contrast of loss from the projection layer and the cross-entropy loss from the classification layer. This ensures the convergence of the adaptive learning rate strategy. Experimental results demonstrate that the proposed method achieves competitive performance compared to other state-of-the-art methods. This article was authored by Yucheng Zhao, Qianli, Xianglu, and others.