Federated Inference: Towards Collaborative and Privacy-Preserving Inference over Edge Devices
Year: 2025
Type: conference-paper
Abstract: The growing AI capabilities on edge devices, along with increasing privacy concerns, call for new paradigms for distributed inference. We introduce Federated Inference (FI), a novel framework enabling multiple heterogeneous edge devices to collaboratively execute complex inference tasks on local data without revealing private information. FI pioneers the first design of capability-aware, privacy-preserving model partitioning, where a central orchestra-tor adaptively splits models based on individual client profiles. To ensure privacy, FI injects calibrated differential privacy noise into intermediate activations before transmission. We prototype FI and demonstrate that our adaptive-split strategy significantly reduces latency for weak clients while maintaining privacy and communication efficiency.
Authors: Boyu Fan, Xiang Su, Sasu Tarkoma, Pan Hui
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: Tekniikan Edistämissäätiö
OpenAlex ID: W4414109557