Towards Integrated Fine-tuning and Inference when Generative AI meets Edge Intelligence
This work addresses the problem of contradictory features between GAI and EI for enabling efficient fine-tuning and inference in edge computing, though it appears incremental as it builds on existing concepts of cloud-edge collaboration.
The paper tackles the challenge of integrating generative AI (GAI) with edge intelligence (EI) by proposing GaisNet, a collaborative framework that uses data-free knowledge relay to enable bidirectional knowledge flow, achieving mutualism between GAI and EI with seamless fusion.
The high-performance generative artificial intelligence (GAI) represents the latest evolution of computational intelligence, while the blessing of future 6G networks also makes edge intelligence (EI) full of development potential. The inevitable encounter between GAI and EI can unleash new opportunities, where GAI's pre-training based on massive computing resources and large-scale unlabeled corpora can provide strong foundational knowledge for EI, while EI can harness fragmented computing resources to aggregate personalized knowledge for GAI. However, the natural contradictory features pose significant challenges to direct knowledge sharing. To address this, in this paper, we propose the GAI-oriented synthetical network (GaisNet), a collaborative cloud-edge-end intelligence framework that buffers contradiction leveraging data-free knowledge relay, where the bidirectional knowledge flow enables GAI's virtuous-cycle model fine-tuning and task inference, achieving mutualism between GAI and EI with seamless fusion and collaborative evolution. Experimental results demonstrate the effectiveness of the proposed mechanisms. Finally, we discuss the future challenges and directions in the interplay between GAI and EI.