Federated graph learning has been widely used in distributed graph machine learning tasks. The data distribution of existing graph-based federated Spatio-temporal prediction methods is mainly segmented by graph topolo...
详细信息
Human microchip implants are small devices that are implanted into the body for various purposes including storing and transmitting information, monitoring health or location, and providing access to facilities or sys...
详细信息
There has been an increasing interest in enhancing the fairness of machine learning (ML). Despite the growing number of fairness-improving methods, we lack a systematic understanding of the trade-offs among factors co...
There has been an increasing interest in enhancing the fairness of machine learning (ML). Despite the growing number of fairness-improving methods, we lack a systematic understanding of the trade-offs among factors considered in the ML pipeline when fairness-improving methods are applied. This understanding is essential for developers to make informed decisions regarding the provision of fair ML services. Nonetheless, it is extremely difficult to analyze the trade-offs when there are multiple fairness parameters and other crucial metrics involved, coupled, and even in conflict with one another. This paper uses causality analysis as a principled method for analyzing trade-offs between fairness parameters and other crucial metrics in ML pipelines. To practically and effectively conduct causality analysis, we propose a set of domain-specific optimizations to facilitate accurate causal discovery and a unified, novel interface for trade-off analysis based on well-established causal inference methods. We conduct a comprehensive empirical study using three real-world datasets on a collection of widely-used fairness-improving techniques. Our study obtains actionable suggestions for users and developers of fair ML. We further demonstrate the versatile usage of our approach in selecting the optimal fairness-improving method, paving the way for more ethical and socially responsible AI technologies.
To alleviate the pressure on storage and execution on blockchain, existing platforms such as Ethereum have designed payment channels, attempting to transfer some of the pressure to off chain. Consistency protocols suc...
详细信息
Accurate recognition of AI-generated images is critical for information security and disinformation prevention in the media. Traditional image recognition models face challenges in recognizing images produced by advan...
详细信息
As a computing paradigm tailored for resource-constrained client devices, federated learning based on model pruning compresses the model size by removing unimportant parameters in the neural network, which has shown o...
详细信息
Rapidly increasing data requires a lot of time to execute different tasks by the systems at Cloudlet Federation (CF). The demand of today's computing is to exploit resource utilization up to maximum. Efficient res...
详细信息
In this paper, a prediction model of heart disease based on the optimized algorithm of decision tree is proposed to solve the problem that the prediction accuracy of decision tree model is not high in the traditional ...
详细信息
The growing incidence of Non-Hodgkin lymphomas (NHL) in recent times has brought attention to the need for thorough investigations of their genetic associations with autoimmune and rheumatologic conditions, such as sy...
详细信息
The growing incidence of Non-Hodgkin lymphomas (NHL) in recent times has brought attention to the need for thorough investigations of their genetic associations with autoimmune and rheumatologic conditions, such as systemic lupus, celiac disease, and Sj & ouml;gren's syndrome. Our study is the first of its type in this field since it uses machine learning to investigate these relationships in great detail. Firstly, we have developed a new genetic dataset, specifically designed to uncover the genetic intricacies of NHL and rheumatologic diseases, offering unprecedented insights into their molecular mechanisms. Following this, we introduced the Clustered-Based Binary Grey Wolf Optimizer (CB-BGWO), a novel method that significantly revolutionizes the feature selection process in genetic analysis. This optimizer significantly improves the accuracy and efficiency of identifying important genetic variables affecting the interaction between rheumatologic and NHL illnesses. This methodological advance not only increases the analytical power but also creates a new standard for genetic research methods. Our findings address a significant gap in the literature and offer valuable insights that could positively support future treatment strategies and research paths. By illuminating the complex genetic connections between NHL and significant rheumatologic conditions, this work contributes to a better understanding and treatment of these complex diseases.
暂无评论