iDOL: incentivized decentralized opportunistic learning

With the emergence of decentralized and opportunistic approaches to machine learning, end devices increasingly train models on-device using crowd-sourced data they collect themselves. These approaches are desirable from a resource perspective and also from a privacy perspective. When the devices benefit directly from the trained models, the incentives are implicit - contributing devices are incentivized by the availability of the higher-accuracy model that results from collaboration. However, explicit incentives must be provided when end-user devices are asked to contribute their resources (e.g., computation, communication, and data) to a task performed primarily for the benefit of others, e.g., training a model for a task that the device owner is uninterested in. We propose a novel blockchain-based incentive mechanism for completely decentralized and opportunistic learning architectures. We leverage a smart contract not only for providing explicit incentives to end devices to participate in decentralized learning but also to create a fully decentralized mechanism to inspect and reflect on the behavior of the learning architecture.