Visual Evolutionary Optimization on Graph-Structured Combinatorial Problems with MLLMs: A Case Study of Influence Maximization
IEEE Transactions on Evolutionary Computation · 2026-08 · 30 (4) · 1714-1728
DOI: 10.1109/tevc.2025.3598266 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Evolutionary Computation, 2026-08. Verfasst von Jie Zhao und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: Singapore Ministry of Education (MOE) Science of Learning.
Abstract (Originalsprache)
Graph-structured combinatorial problems in complex networks are prevalent in many domains, and are computationally demanding due to their complexity and nonlinear nature. Traditional evolutionary algorithms (EAs), while robust, often face obstacles due to content-shallow encoding limitations and lack of structural awareness, necessitating hand-crafted modifications for effective application. In this work, we introduce an original framework, visual evolutionary optimization (VEO), leveraging multimodal large language models (MLLMs) as the backbone evolutionary optimizer in this context. Specifically, we propose a context-aware encoding scheme, representing the solution of the network as an image. In this manner, we can utilize MLLMs’ image processing capabilities to intuitively comprehend network configurations, thus enabling machines to solve these problems in a human-like way. We develop MLLM-based operators tailored for various evolutionary optimization stages, including initialization, crossover, and mutation. Furthermore, we propose that graph sparsification can effectively enhance the applicability and scalability of VEO on large-scale networks, owing to the scale-free nature of real-world networks. We demonstrate the effectiveness of our method using a well-known task in complex networks, influence maximization, and validate it on eight different real-world networks of various structures. The results confirm VEO’s reliability and enhanced effectiveness compared to traditional evolutionary optimization.
Förderung
- Singapore Ministry of Education (MOE) Science of Learning
Zitieren
APA
Zhao, J., & Cheong, K. H. (2026). Visual Evolutionary Optimization on Graph-Structured Combinatorial Problems with MLLMs: A Case Study of Influence Maximization. IEEE Transactions on Evolutionary Computation, 30(4), 1714-1728. https://doi.org/10.1109/tevc.2025.3598266
Vancouver
Zhao J, Cheong KH. Visual Evolutionary Optimization on Graph-Structured Combinatorial Problems with MLLMs: A Case Study of Influence Maximization. IEEE Transactions on Evolutionary Computation. 2026;30(4):1714-1728. doi:10.1109/tevc.2025.3598266
BibTeX
@article{Zhao2026,
author = {Zhao, Jie and Cheong, Kang Hao},
title = {Visual Evolutionary Optimization on Graph-Structured Combinatorial Problems with MLLMs: A Case Study of Influence Maximization},
journal = {IEEE Transactions on Evolutionary Computation},
year = {2026},
volume = {30},
number = {4},
pages = {1714--1728},
doi = {10.1109/tevc.2025.3598266}
}
EUVIMED