Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
This addresses transparency and trustworthiness issues in FL for AI engineering and ethics, though it is incremental as it builds on existing AI FactSheets.
The paper tackles the problem of ensuring accountability and reproducibility in Federated Learning (FL) by introducing the AF^2 Framework, which uses verifiable claims and tamper-evident facts to create reproducible arguments, enabling auditors to validate and certify FL processes.
Federated Learning (FL) is a novel paradigm for the shared training of models based on decentralized and private data. With respect to ethical guidelines, FL is promising regarding privacy, but needs to excel vis-à-vis transparency and trustworthiness. In particular, FL has to address the accountability of the parties involved and their adherence to rules, law and principles. We introduce AF^2 Framework, where we instrument FL with accountability by fusing verifiable claims with tamper-evident facts, into reproducible arguments. We build on AI FactSheets for instilling transparency and trustworthiness into the AI lifecycle and expand it to incorporate dynamic and nested facts, as well as complex model compositions in FL. Based on our approach, an auditor can validate, reproduce and certify a FL process. This can be directly applied in practice to address the challenges of AI engineering and ethics.