Goal-Oriented Ordered Autoencoding for Successive Refinement in Progressive Communication
Abstract
Goal-oriented communication often struggles to sustain downstream task performance under variable and unpredictable bandwidth. We address this problem by proposing GO-OAE (Goal-Oriented Ordered AutoEncoding), which learns a progressively refinable quantized latent sequence, optimized directly for task utility rather than source reconstruction. Each component of the sequence is represented for transmission by its code index, and the learned ordering enables inference from any received prefix of the index sequence, with performance improving as more indices arrive. We prove that optimizing the goal-oriented distortion objective is equivalent to solving a weighted conditional information bottleneck formulation, and introduce an unbiased multi-prefix importance sampling (MPIS) estimator, to reduce GO-OAE training computational cost from O(BK) to O(Bm) with m << K, and reduces the estimator variance by a factor of 1/m. Experiments show that, on MiniImageNet, GO-OAE achieves over 96% of the lossless upper-bound classification accuracy using 324 bits per image (683X compression vs. raw RGB), and already attains over 94% of the upper bound with only 70% of the transmitted indices. It consistently outperforms reconstruction-optimized codecs and ordered autoencoders trained with uniform prefix sampling across all transmission budgets, demonstrating effective communication at extreme compression rates.
Related
- Cross-Modal Semantic Successive Refinement for Generative Image Communication over Underwater Acoustic Channels
- Successive Refinement Under Strong-Sense Perfect Perception
- Progressive Reliability-Guided Refinement with Cross-Modal Consistency and Iterative Correction for Weakly Supervised PET/CT Tumor Segmentation
- MAP-Based Task-Oriented Precoding for Multiuser Communication
- More Interactions Make Communications More Efficient: A Directed Information Bottleneck Approach to Task-Oriented Communication
BibTeX
@misc{liao2026goaloriented,
title = {{Goal-Oriented Ordered Autoencoding for Successive Refinement in Progressive Communication}},
author = {Qi Liao and Dario Bega},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.13426},
eprint = {2610.13426},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.13426},
}
RIS
TY - UNPB
TI - Goal-Oriented Ordered Autoencoding for Successive Refinement in Progressive Communication
AU - Qi Liao
AU - Dario Bega
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.13426
UR - https://arxiv.org/abs/2610.13426
AB - Goal-oriented communication often struggles to sustain downstream task performance under variable and unpredictable bandwidth. We address this problem by proposing GO-OAE (Goal-Oriented Ordered AutoEncoding), which learns a progressively refinable quantized latent sequence, optimized directly for task utility rather than source reconstruction. Each component of the sequence is represented for transmission by its code index, and the learned ordering enables inference from any received prefix of the index sequence, with performance improving as more indices arrive. We prove that optimizing the goal-oriented distortion objective is equivalent to solving a weighted conditional information bottleneck formulation, and introduce an unbiased multi-prefix importance sampling (MPIS) estimator, to reduce GO-OAE training computational cost from O(BK) to O(Bm) with m << K, and reduces the estimator variance by a factor of 1/m. Experiments show that, on MiniImageNet, GO-OAE achieves over 96% of the lossless upper-bound classification accuracy using 324 bits per image (683X compression vs. raw RGB), and already attains over 94% of the upper bound with only 70% of the transmitted indices. It consistently outperforms reconstruction-optimized codecs and ordered autoencoders trained with uniform prefix sampling across all transmission budgets, demonstrating effective communication at extreme compression rates.
ER -