Self-Organization Preserved Graph Structure Learning with Principle of Relevant Information

Most Graph Neural Networks follow the message-passing paradigm, assuming observed structure depicts ground-truth node relationships. However, this fundamental assumption cannot always be satisfied, as real-world graphs are incomplete, noisy, or redundant. How to reveal inherent graph in a unified way remains under-explored. We proposed PRI-GSL, Structure Learning framework guided by Principle of Relevant Information, providing simple and for identifying self-organization revealing hidden structure. PRI-GSL learns that contains most relevant yet least redundant information quantified von Neumann entropy Quantum Jensen Shannon divergence. incorporates evolution quantum continuous walk with wavelets encode structural roles, showing which nodes interplay self-organize Extensive experiments demonstrate superior effectiveness robustness PRI-GSL.