Preprint
Jul 2026
Positional Attention-based Graph Neural Network for Learning Permutation Non-equivariant Wireless Policies
This paper proposes a novel positional attention-based GNN to learn permutation nonequivariant policies efficiently, and employs the proposed GNN to learn the policies, where the embedding function is designed based on the channel covariance matrix.
Baichuan Zhao, Chen-Yang Yang, Jianyu Zhao et al.
· 0 citations