Enhancing the Performance of Global Optimization of Platinum Cluster Structures by Transfer Learning in a Deep Neural Network

The global optimization of metal cluster structures is an important research field. The traditional deep neural network (T-DNN) global optimization method is a good way to find out the global minimum (GM) of metal cluster structures, but a large number of samples are required. We developed a new global optimization method which is the combination of the DNN and transfer learning (DNN-TL). The DNN-TL method transfers the DNN parameters of the small-sized cluster to the DNN of the large-sized cluster to greatly reduce the number of samples. For the global optimization of Pt9 and Pt13 clusters in this research, the T-DNN method requires about 3-10 times more samples than the DNN-TL method, and the DNN-TL method saves about 70-80% of time. We also found that the average amplitude of parameter changes in the T-DNN training is about 2 times larger than that in the DNN-TL training, which rationalizes the effectiveness of transfer learning. The average fitting errors of the DNN trained by the DNN-TL method can be even smaller than those by the T-DNN method because of the reliability of transfer learning. Finally, we successfully obtained the GM structures of Ptn (n = 8-14) clusters by the DNN-TL method.

Automated summary

The global optimization of metal cluster structures is a significant research area, with traditional deep neural network (T-DNN) method being a good approach but requiring numerous samples. We proposed a new method called DNN-TL that combines deep neural network and transfer learning, reducing the number of samples needed. Comparing to the T-DNN method, the DNN-TL method requires only a fraction of the samples and saves 70-80% of time for the global optimization of Pt9 and Pt13 clusters in this research. The effectiveness of transfer learning is rationalized by the larger amplitude of parameter changes in T-DNN compared to DNN-TL training. Additionally, the DNN trained by the DNN-TL method achieves even smaller fitting errors than the T-DNN method due to the reliability of transfer learning. Finally, the DNN-TL method successfully obtained the global minimum structures of Ptn (n = 8-14) clusters.