Differential evolution (DE) is widely used in numerical optimization, but fixed parameters and a single mutation strategy make it difficult to coordinate exploration and exploitation across different search stages. To address this issue, this paper proposes Bio-EbDE, a DE algorithm with stage-aware mutation strategy switching, subpopulation-specific parameter adaptation, and a local optimum escape mechanism. Its main distinction lies in three coordinated designs: mutation strategies are selected according to both evolutionary stage and subpopulation role; the scaling factor F is generated from different distributions for different subpopulations; and a spray-melon-inspired perturbation generates offspring with adaptive dispersal when premature convergence is detected. Experiments on CEC2013, CEC2022, and a constrained engineering problem show that Bio-EbDE achieves competitive optimization accuracy and convergence behavior.
Xia-Min Deng, Qun Liu· 2026 12th International Conf...· 0 citations
Molecular property prediction provides an important computational basis for compound screening and drug development by estimating physicochemical characteristics and biological activities from molecular structures. Although deep learning has improved molecular modeling, existing methods often describe molecules through a limited structural view or combine multiple views without sufficiently exploiting their complementary relationships. In addition, graph-based approaches commonly concentrate on local atomic connectivity, making it difficult to represent chemically meaningful structural units that may strongly influence molecular properties. This paper develops MG-CMIF, a multi-granularity cross-modal framework for molecular property prediction. The proposed model describes each molecule from symbolic, topological, and spatial perspectives and learns an integrated representation through three key designs. First, hierarchical graph modeling combines detailed atomic interactions with substructure-level chemical patterns to enrich topology-oriented features. Second, interaction across molecular views enables information relevant to property prediction to be exchanged selectively rather than merged through shallow operations. Third, alignment-oriented training objectives encourage representations derived from the same molecule to preserve compatible chemical semantics during fusion. Experiments on multiple public benchmark datasets show that MG-CMIF achieves better prediction results than competitive methods in both classification and regression settings. Further ablation analyses confirm that hierarchical structural modeling and cross-view integration both contribute to the effectiveness of the proposed framework.
Qun Liu, Mao-Yuan Zang, Rui Han et al.· Journal of Machine Learning...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
