To improve the performance of Quantum-inspired Evolutionary algorithm based on P Systems (QEPS), this paper presents an improved QEPS with a Dynamic Membrane Structure (QEPS-DMS) to solve knapsack problems. QEPS-DMS combines quantum-inspired evolutionary algorithms (QIEAs) with a P system with a dynamic membrane structure. In QEPS-DMS, a QIEA is considered as a subalgorithm to put inside each elementary membrane of a one-level membrane structure, which is dynamically adjusted in the process of evolution by applying a criterion for measuring population diversity. The dynamic adjustment includes the processes of membrane dissolution and creation. Knapsack problems are applied to test the effectiveness of QEPS-DMS. Experimental results show that QEPS-DMS outperforms QEPS and three variants of QIEAs recently reported in the literature.
Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming the observed structure perfectly depicts the accurate and complete relations between nodes. However, graphs in the real-world are inevitably noisy or incomplete, which could even exacerbate the quality of graph representations. In this work, we propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL, in the perspective of information theory. VIB-GSL is the first attempt to advance the Information Bottleneck (IB) principle for graph structure learning, providing a more elegant and universal framework for mining underlying task-relevant relations. VIB-GSL learns an informative and compressive graph structure to distill the actionable information for specific downstream tasks. VIB-GSL deduces a variational approximation for irregular graph data to form a tractable IB objective function, which facilitates training stability. Extensive experimental results demonstrate that the superior effectiveness and robustness of the proposed VIB-GSL.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.