Abstract: In order to solve the problem that it is difficult to obtain complete and effective historical power data from the power grid and unable to make full use of the spatio-temporal correlation ...

Abstract: Graph neural network (GNN) models are capable of capturing the intrinsic structure and semantic relationships within data and this mechanism grants them substantial potential advantages in ...

In this paper, we tackle the high computational overhead of transformers for lightweight image super-resolution. (SR). Motivated by the observations of self-attention's inter-layer repetition, we ...