Search

Abstract In this paper, a framework based on a sparse Mixture of Experts (MoE) architecture is proposed for the federated learning and application of a distributed classification model in domains (like cybersecurity and healthcare) where different parties of the federation store different subsets of features for a number of data instances. The framework is designed to limit the risk of information leakage and computation/communication costs in both model training (through data sampling) and application (leveraging the conditional-computation abilities of sparse MoEs). Experiments on real data have shown the proposed approach to ensure a better balance between efficiency and model accuracy, compared to other VFL-based solutions. Notably, in a real-life cybersecurity case study focused on malware classification (the KronoDroid dataset), the proposed method surpasses competitors even though it utilizes only 50% and 75% of the training set, which is fully utilized by the other approaches in the competition. This method achieves reductions in the rate of false positives by 16.9% and 18.2%, respectively, and also delivers satisfactory results on the other evaluation metrics. These results showcase our framework’s potential to significantly enhance cybersecurity threat detection and prevention in a collaborative yet secure manner.

MC-PSC (Multi-Criteria Protein Structure Comparison) is one of the GCAs (Grand Challenge Applications) in the field of structural proteomics. The solution of the MC-PSC grand challenge requires the use of distributed algorithms, architectures and environments. This paper is aimed at the analysis of the scalability of our newly developed distributed algorithm for MC-PSC in the grid environment. The scalability in the grid environment indicates the capacity of the distributed algorithm to effectively utilize an increasing number of processors across multiple sites. The results of the experiments conducted on the UK's NGS (National Grid Service) infrastructure are reported in terms of speedup, efficiency and cross-site communication overhead.