CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge
arXiv:2601.00549v2 Announce Type: replace-cross Abstract: The deployment of large-scale neural networks within the Open Radio Access Network (O-RAN) architecture is pivotal for enabling native edge intelligence. However, this paradigm faces two critical bottlenecks: the prohibitive memory footprint required for local training on resource-constrained gNBs, and the saturation of bandwidth-limited backhaul links during the global aggregation of high-dimensional model updates. To address these challenges, we propose CoCo-Fed, a novel Compression and Combination-based Federated learning framework t
The proliferation of large-scale AI models necessitates more efficient edge computing solutions, especially within evolving wireless network architectures like O-RAN.
This research addresses critical bottlenecks in deploying advanced AI at the wireless edge, potentially enabling more widespread and powerful AI capabilities in remote or resource-constrained environments.
The proposed CoCo-Fed framework offers a path to overcome memory and communication limitations in federated learning for edge intelligence, making practical deployment more feasible.
- · Telecommunication companies
- · Edge AI providers
- · Hardware manufacturers for edge devices
- · 5G/6G infrastructure developers
- · Traditional centralized cloud AI models
- · Companies reliant on high-bandwidth backhaul for all AI processing
More efficient deployment of federated learning models on resource-constrained edge devices.
Accelerated development and adoption of AI-driven applications directly within wireless networks, enhancing services like autonomous vehicles and smart cities.
Reduced dependency on hyperscale cloud data centers for certain types of AI inference and learning, fostering a more distributed and resilient AI ecosystem.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI