Improving Heterogeneous Network Knowledge Transfer Based on the Principle of Generative Adversarial

Abstract

Deep learning requires a large amount of datasets to train deep neural network models for specific tasks, and thus training of a new model is a very costly task. Research on transfer networks used to reduce training costs will be the next turning point in deep learning research. The use of source task models to help reduce the training costs of the target task models, especially heterogeneous systems, is a problem we are studying. In order to quickly obtain an excellent target task model driven by the source task model, we propose a novel transfer learning approach. The model linearly transforms the feature mapping of the target domain and increases the weight value for feature matching to realize the knowledge transfer between heterogeneous networks and add a domain discriminator based on the principle of generative adversarial to speed up feature mapping and learning. Most importantly, this paper proposes a new objective function optimization scheme to complete the model training. It successfully combines the generative adversarial network with the weight feature matching method to ensure that the target model learns the most beneficial features from the source domain for its task. Compared with the previous transfer algorithm, our training results are excellent under the same benchmark for image recognition tasks.

Classification Algorithm for Heterogeneous Network Data Streams Based on Big Data Active Learning

“…Lei et al used source task models to help reduce the training cost of target task models in order to reduce the neural network training cost. They proposed a new migration learning method which linearly transforms the feature mapping of the target region, increases the weights of feature matching, enables knowledge transfer between heterogeneous networks, and adds discriminators based on adversarial principles to speed up feature mapping and learning [10]. Sharipuddin et al addressed the intrusion detection system in heterogeneous networks which is easily affected by objective factors such as devices and network protocols, proposed an identification method combining deep learning, and conducted preliminary experiments on denial-of-service attacks, and the experimental results showed that deep learning can improve the detection accuracy in heterogeneous networks [11].…”

GrCol-PPFL: User-Based Group Collaborative Federated Learning Privacy Protection Framework

“…Currently, data is still in the form of isolated islands due to issues such as competitive relationships and trust levels among industries, enterprises, and even individuals. Traditional distributed machine learning [5,6] collects all data for unified training. However, in many applications, data is scattered among mobile edge devices and cannot be shared and transmitted safely and effectively.…”

An Improved BPNN Prediction Method Based on Multi-Strategy Sparrow Search Algorithm

“…In the era of big data, the field of artificial intelligence is making a splash, [1][2][3][4][5][6][7][8]. Accurate prediction plays a crucial role in our modern life, where the research of prediction methods based on machine learning, especially neural networks, has become increasingly popular, [9][10][11][12].…”