Bipartite subgraph problem is an important example of a class of combinatorial optimization problems. It has many important applications in modeling matching problem, modern coding theory, communication network, and computer science. The goal of this NP‐complete problem is to find a bipartite subgraph with maximum number of edges of the given graph. In this paper, for efficiently solving the problem, we propose a genetic algorithm‐based approach in which the genetic operators are performed based on the condition instead of probability. The proposed algorithm is tested on a large number of instances, and the experimental results show that the proposed algorithm is superior to its competitors. Copyright © 2009 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.