CALTeC: Content-Adaptive Linear Tensor Completion for Collaborative Intelligence
This addresses packet loss issues in edge-cloud AI systems, but it appears incremental as it builds on existing tensor completion techniques.
The paper tackles the problem of missing feature tensors due to packet loss in collaborative intelligence systems by proposing CALTeC, a fast, data-adaptive method that recovers missing data without pre-training and outperforms existing tensor recovery methods.
In collaborative intelligence, an artificial intelligence (AI) model is typically split between an edge device and the cloud. Feature tensors produced by the edge sub-model are sent to the cloud via an imperfect communication channel. At the cloud side, parts of the feature tensor may be missing due to packet loss. In this paper we propose a method called Content-Adaptive Linear Tensor Completion (CALTeC) to recover the missing feature data. The proposed method is fast, data-adaptive, does not require pre-training, and produces better results than existing methods for tensor data recovery in collaborative intelligence.