CALTeC: Content-Adaptive Linear Tensor Completion for Collaborative Intelligence
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.
Code (1)
Similar Papers 제목 키워드 기반
JULIA: Joint Multi-linear and Nonlinear Identification for Tensor Completion
Tensor completion aims at imputing missing entries from a partially observed tensor. Existing tensor completion methods often assume either multi-linear or nonlinear relationships between latent components. However, real…
Model SelectionDictionary Learning with Low-rank Coding Coefficients for Tensor Completion
In this paper, we propose a novel tensor learning and coding model for third-order data completion. Our model is to learn a data-adaptive dictionary from the given observations, and determine the coding coefficients of t…
Dictionary LearningMulti-Tensor Network Representation for High-Order Tensor Completion
This work studies the problem of high-dimensional data (referred to as tensors) completion from partially observed samplings. We consider that a tensor is a superposition of multiple low-rank components. In particular, e…
Tensor DecompositionVocal Bursts Intensity PredictionLow-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms
This work studies the low-rank tensor completion problem, which aims to exactly recover a low-rank tensor from partially observed entries. Our model is inspired by the recently proposed tensor-tensor product (t-product) …
Beyond Low Rank: A Data-Adaptive Tensor Completion Method
Low rank tensor representation underpins much of recent progress in tensor completion. In real applications, however, this approach is confronted with two challenging problems, namely (1) tensor rank determination; (2) h…