Opportunistic Federated Learning: An Exploration of Egocentric Collaboration for Pervasive Computing Applications

Abstract

Pervasive computing applications commonly involve user's personal smartphones collecting data to influence application behavior. Applications are often backed by models that learn from the user's experiences to provide personalized and responsive behavior. While models are often pre-trained on massive datasets, federated learning has gained attention for its ability to train globally shared models on users' private data without requiring the users to share their data directly. However, federated learning requires devices to collaborate via a central server, under the assumption that all users desire to learn the same model. We define a new approach, opportunistic federated learning, in which individual devices belonging to different users seek to learn robust models that are personalized to their user's own experiences. However, instead of learning in isolation, these models opportunistically incorporate the learned experiences of other devices they encounter opportunistically. In this paper, we explore the feasibility and limits of such an approach, culminating in a framework that supports encounter-based pairwise collaborative learning. The use of our opportunistic encounter-based learning amplifies the performance of personalized learning while resisting overfitting to encountered data.

Knowledge Sharing in AI Services: A Market-Based Approach

“…Local models are also combined with multi-stage parameter relaying between layers in a tree-like structure. Lee et al [42] introduce the concept of opportunistic FL in which individual devices belonging to different users learn models personalized to the user's experience. These devices then incorporate new knowledge as they encounter each other by exchanging model parameters and gradients.…”

Semi-supervised and personalized federated activity recognition based on active learning and label propagation

“…Among the required characteristics of FL approaches, the personalization of the global model on each client plays a major role [43] FL has been previously applied to mobile/wearable HAR to distribute the training of the activity recognition model among the participating devices [8,11,[44][45][46][47][48]. In this area, recent works also proposed to learn the global model in a decentralized fashion [49]. Existing works show that FL solutions for HAR reach recognition accuracy similar to standard centralized models [45].…”

BOppCL: Blockchain-Enabled Opportunistic Federated Learning Applied in Intelligent Transportation Systems

“…OppCL [14] provided a distributed decentralized security method for the sharing of data between autonomous vehicles in ITS. By storing local data at vehicle nodes, vehicles exchange gradients with other vehicles based on opportunistic encounters and train local models, privacy issues are solved much more, and data transmission costs are reduced.…”