Heuristic algorithms have been developed to find approximate solutions for high-utility itemset mining (HUIM) problems that compensate for the performance bottlenecks of exact algorithms. However, heuristic algorithms still face the problem of long runtime and insufficient mining quality, especially for large transaction datasets with thousands to tens of thousands of items and up to millions of transactions. To solve these problems, a novel GPU-based efficient parallel heuristic algorithm for HUIM (PHA-HUIM) is proposed in this paper. The iterative process of PHA-HUIM consists of three main steps: the search strategy, fitness evaluation, and ring topology communication. The search strategy and ring topology communication are designed to run in constant time on GPU. The parallelism of fitness evolution helps to substantially accelerate the algorithm. To improve the mining quality, a multi-start strategy with an unbalanced allocation strategy is employed in the search process. Ring topology communication is adopted to maintain population diversity. A load balancing strategy is introduced to reduce the thread divergence to improve the parallel efficiency. The experimental results on nine large datasets show that PHA-HUIM outperforms state-of-the-art HUIM algorithms in terms of speedup performance, runtime, and mining quality.

Bayesian network structure learning (BNSL) from data is an NP-hard problem. Genetic algorithms are powerful for solving combinatorial optimization problems, but the lack of effective guidance results in slow convergence and low accuracy regarding BNSL. To address this problem, we propose a mutual information (MI) guided genetic algorithm (MIGA) for BNSL in this paper, which uses MI to effectively search BN structures. In the initialization phase of MIGA, the population is generated by adding additional constraints based on MI to reach a higher score without losing diversity. By employing normalized MI and defining the population support, the potential dominance in the population can be identified and then used to design a novel crossover operator in order to preserve the dominant genes with a higher probability. Moreover, with the guidance of MI for removing loops from the structures, infeasible solutions can be handled in a straightforward and practical way. The proposed MIGA is evaluated on eleven well-known benchmark datasets and compared with four GA-based methods and four other state-of-the-art BNSL algorithms. Experimental results show that MIGA outperforms the compared algorithms in convergence and learning accuracy.

Heuristic algorithms have been developed to find approximate solutions for high-utility itemset mining (HUIM) problems that compensate for the performance bottlenecks of exact algorithms. However, heuristic algorithms still face the problem of long runtime and insufficient mining quality, especially for large transaction datasets with thousands to tens of thousands of items and up to millions of transactions. To solve these problems, a novel GPU-based efficient parallel heuristic algorithm for HUIM (PHA-HUIM) is proposed in this paper. The iterative process of PHA-HUIM consists of three main steps: the search strategy, fitness evaluation, and ring topology communication. The search strategy and ring topology communication are designed to run in constant time on GPU. The parallelism of fitness evolution helps to substantially accelerate the algorithm. A new data structure with a sort-mapping strategy is proposed to enhance the search ability and reduce memory usage. To improve the mining quality, a multi-start strategy with an unbalanced allocation strategy is employed in the search process. Ring topology communication is adopted to maintain population diversity. A load balancing strategy is introduced to reduce the thread divergence to improve the parallel efficiency. The experimental results on nine large datasets show that PHA-HUIM outperforms state-of-the-art HUIM algorithms in terms of speedup performance, runtime, and mining quality.

Bayesian network structure learning (BNSL) from data is an NP-hard problem. Genetic algorithms are powerful for solving combinatorial optimization problems, but the lack of effective guidance results in slow convergence and low accuracy regarding BNSL. To address this problem, we propose a mutual information (MI) guided genetic algorithm (MIGA) for BNSL in this paper, which uses MI to effectively search BN structures. In the initialization phase of MIGA, the population is generated by adding additional constraints based on MI to reach a higher score without losing diversity. By employing normalized MI and defining the population support, the potential dominance in the population can be identified and then used to design a novel crossover operator in order to preserve the dominant genes with a higher probability. Moreover, with the guidance of MI for removing loops from the structures, infeasible solutions can be handled in a straightforward and practical way. The proposed MIGA is evaluated on eleven well-known benchmark datasets and compared with four GA-based methods and four other state-of-the-art BNSL algorithms. Experimental results show that MIGA outperforms the compared algorithms in convergence and learning accuracy.