eccCL: parallelized GPU implementation of Ensemble Classifier Chains

Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction

Current 5G communication services have limitations, prompting the development of the Beyond 5G (B5G) network. B5G aims to extend the scope of communication to encompass land, sea, air, and space while enhancing communication intelligence and evolving into an omnipresent converged information network. This expansion demands higher standards for communication rates and intelligent processing across multiple devices. Furthermore, traffic prediction is crucial for the intelligent and efficient planning and management of communication networks, optimizing resource allocation, and enhancing network performance and communication speeds and is an important part of B5G's performance. Federated learning addresses privacy and transmission cost issues in model training, making it widely applicable in traffic prediction. However, traditional federated learning models are susceptible to adversarial attacks that can compromise model outcomes. To safeguard traffic prediction from such attacks and ensure the reliability of the prediction system, this paper introduces the Adaptive Threshold Modified Federated Forest (ATMFF). ATMFF employs adaptive threshold modification, utilizing a confusion matrix rate-based screening-weighted aggregation of weak classifiers to adjust the decision threshold. This approach enhances the accuracy of recognizing adversarial samples, thereby ensuring the reliability of the traffic prediction model. Our experiments, based on real 5G traffic data, demonstrate that ATMFF's adversarial sample recognition accuracy surpasses that of traditional multiboost models and models without adaptive threshold modified. This improvement bolsters the security and reliability of intelligent traffic classification services.

Federated Random Forests can improve local performance of predictive models for various healthcare applications

MOTIVATION

Limited data access has hindered the field of precision medicine from exploring its full potential, e.g. concerning machine learning and privacy and data protection rules.Our study evaluates the efficacy of federated Random Forests (FRF) models, focusing particularly on the heterogeneity within and between datasets. We addressed three common challenges: (i) number of parties, (ii) sizes of datasets and (iii) imbalanced phenotypes, evaluated on five biomedical datasets.

RESULTS

The FRF outperformed the average local models and performed comparably to the data-centralized models trained on the entire data. With an increasing number of models and decreasing dataset size, the performance of local models decreases drastically. The FRF, however, do not decrease significantly. When combining datasets of different sizes, the FRF vastly improve compared to the average local models. We demonstrate that the FRF remain more robust and outperform the local models by analyzing different class-imbalances.Our results support that FRF overcome boundaries of clinical research and enables collaborations across institutes without violating privacy or legal regulations. Clinicians benefit from a vast collection of unbiased data aggregated from different geographic locations, demographics and other varying factors. They can build more generalizable models to make better clinical decisions, which will have relevance, especially for patients in rural areas and rare or geographically uncommon diseases, enabling personalized treatment. In combination with secure multi-party computation, federated learning has the power to revolutionize clinical practice by increasing the accuracy and robustness of healthcare AI and thus paving the way for precision medicine.

AVAILABILITY AND IMPLEMENTATION

The implementation of the federated random forests can be found at https://featurecloud.ai/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.