We introduce Federated Learning for Optimizing Resource Allocation (FLORA), an extension to the CINCO de Bio (CdB)1platform for health analysis workflows. FLORA uses Federated Learning (FL) to optimize resource allocation for Service-Independent Building Blocks (SIBs) execution across multiple CdB deployments, predicting maximum memory usage while maintaining privacy. Preliminary results from a matrix multiplication experiment demonstrate the potential of machine learning models to predict peak memory usage of a SIB. We outline the FLORA architecture, discuss its implementation within CdB, and propose future work to validate and integrate the framework in real-world settings.

Train the trainer is a pedagogical model widely used across a range of disciplines and fields. Originating in non- governmental organisations, the model was developed in a bid to reduce costs associated with training while also increasing the capacity of staff to effectively disseminate knowledge within organisations. While its use is now widespread, there is little consensus in the literature regarding its efficacy. This paper describes a train-the-trainer programme that was designed to enhance early-career researchers’ ability to deliver training based on their research. The programme was delivered to a pilot group who then delivered training to external stakeholders on two occasions. The train-the-trainer programme was then evaluated from the perspectives of the trained early-career researchers along with the participants who subsequently took part in workshops delivered by this cohort. Results indicate that the programme was largely successful in improving the early-career researchers’ confidence with respect to training delivery, while also creating a positive learning experience for the participants. The paper concludes with a discussion around the future plans for the development of the train-the-trainer programme based on the results from this pilot implementation.