CALTeC: Content-Adaptive Linear Tensor Completion for Collaborative Intelligence

TL;DR

This paper introduces CALTeC, a fast, data-adaptive tensor completion method that effectively recovers missing feature data in collaborative AI systems without needing pre-training.

Contribution

CALTeC is a novel, efficient tensor completion approach that outperforms existing methods in recovering missing data in collaborative intelligence scenarios.

Findings

CALTeC achieves higher accuracy than existing methods.

The method is fast and does not require pre-training.

It effectively handles missing feature data in real-time applications.

Abstract

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.