Global and Regional Assimilation and Prediction System (GRAPES) is a domestically developed numerical weather prediction system in China. The microphysical process is the key physical process of cloud formation and pr...
详细信息
In the era of bigdata, with the reduction of unit value density of data, it is more meaningful to fully mine the value contained in data resources than to expand the scale of data. Artificial intelligence based on da...
详细信息
In recent years, there has been a rapid growth in interest of using network-based machine learning. They offer the capacity to handle data that exist on irregular and complex structure with interactions between data p...
详细信息
ISBN:
(纸本)9781665421973
In recent years, there has been a rapid growth in interest of using network-based machine learning. They offer the capacity to handle data that exist on irregular and complex structure with interactions between data points. In this paper, we present a semi-supervised regression model utilizing network-based Gaussian process. The proposed method constructs a Gaussian process prior using information from a given network. However, it incurs high computational costs from the required inversions to produce the predictive output and model selection. To overcome the difficulty, we further propose an approximated version that avoids matrix inversion. The proposed method was applied to several regression problems to validate the empirical performance and effectiveness in situations with limited amount of labeled data.
The society has a huge demand for bigdata, artificial intelligence and cloud computing jobs, so it is urgent to cultivate a new generation of information technology talents. On this basis, this paper discusses the st...
详细信息
Under the background of bigdata, traditional aesthetic design thinking is an important professional basic course in current art design teaching. Modern art design is a thinking training for cultivating college studen...
详细信息
As the mainstream development trend of world trade, bigdata has also brought a new direction to the development of international trade theory. Based on the overview of international trade theory, this paper analyzes ...
详细信息
Health is the basis of individual life and the premise of social progress, but its data is difficult to collect, process and synchronize in health management. This leads to difficulties in health prediction and timely...
详细信息
Artificial intelligence is prone to or has caused devastating damage through technical means to access data. But massive amounts of personal information data underpin AI applications;data is the foundation of AI, and ...
详细信息
Federated unlearning has emerged as a promising paradigm to erase the client-level data effect without affecting the performance of collaborative learning models. However, the federated unlearning process often introd...
ISBN:
(纸本)9781956792041
Federated unlearning has emerged as a promising paradigm to erase the client-level data effect without affecting the performance of collaborative learning models. However, the federated unlearning process often introduces extensive storage overhead and consumes substantial computational resources, thus hindering its implementation in practice. To address this issue, this paper proposes a scalable federated unlearning framework based on isolated sharding and coded computing. We first divide distributed clients into multiple isolated shards across stages to reduce the number of clients being affected. Then, to reduce the storage overhead of the central server, we develop a coded computing mechanism by compressing the model parameters across different shards. In addition, we provide the theoretical analysis of time efficiency and storage effectiveness for the isolated and coded sharding. Finally, extensive experiments on two typical learning tasks, i.e., classification and generation, demonstrate that our proposed framework can achieve better performance than three state-of-the-art frameworks in terms of accuracy, retraining time, storage overhead, and F1 scores for resisting membership inference attacks.
Cryptographic functions with low differential uniformity have wide applications in cryptography and cyber security. In this paper, we further investigate c-differential uniformity proposed by Ellingsen et al. (IEEE Tr...
详细信息
暂无评论