Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization

TL;DR

This paper introduces ARTOVeQ, a novel adaptive compression method for remote inference over dynamic links, enabling multi-rate, low-latency, and progressively refined inference with improved flexibility and performance.

Contribution

The paper proposes ARTOVeQ, a learned, adaptive vector quantization scheme that dynamically adjusts to channel conditions and supports progressive, multi-resolution inference.

Findings

Supports multiple bit rates for remote inference.

Enables low-latency, gradually refined inference.

Achieves near single-rate quantization performance.

Abstract

A broad range of technologies rely on remote inference, wherein data acquired is conveyed over a communication channel for inference in a remote server. Communication between the participating entities is often carried out over rate-limited channels, necessitating data compression for reducing latency. While deep learning facilitates joint design of the compression mapping along with encoding and inference rules, existing learned compression mechanisms are static, and struggle in adapting their resolution to changes in channel conditions and to dynamic links. To address this, we propose Adaptive Rate Task-Oriented Vector Quantization (ARTOVeQ), a learned compression mechanism that is tailored for remote inference over dynamic links. ARTOVeQ is based on designing nested codebooks along with a learning algorithm employing progressive learning. We show that ARTOVeQ extends to support low-latency inference that is gradually refined via successive refinement principles, and that it enables the simultaneous usage of multiple resolutions when conveying high-dimensional data. Numerical results demonstrate that the proposed scheme yields remote deep inference that operates with multiple rates, supports a broad range of bit budgets, and facilitates rapid inference that gradually improves with more bits exchanged, while approaching the performance of single-rate deep quantization methods.