# Task-aware Distributed Source Coding under Dynamic Bandwidth

arXiv: https://arxiv.org/abs/2305.15523 · HTML: https://mlsanity.com/paper/2305.15523/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 24 of 24)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Training robust neural networks using Lipschitz bounds](https://mlsanity.com/paper/2005.02929/) (2020)
- [Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection](https://mlsanity.com/paper/2003.01794/) (2020)
- [Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds](https://mlsanity.com/paper/2111.01395/) (2021)
- [Lossy Compression for Lossless Prediction](https://mlsanity.com/paper/2106.10800/) (2021)
- [Neural Distributed Image Compression with Cross-Attention Feature Alignment](https://mlsanity.com/paper/2207.08489/) (2022)
- [Neural Distributed Source Coding](https://mlsanity.com/paper/2106.02797/) (2021)
- [LDMIC: Learning-based Distributed Multi-view Image Coding](https://mlsanity.com/paper/2301.09799/) (2023)
- [Collaborative Semantic Communication for Edge Inference](https://mlsanity.com/paper/2301.03996/) (2023)
- [Task-aware Privacy Preservation for Multi-dimensional Data](https://mlsanity.com/paper/2110.02329/) (2021)
- [Decouple-and-Sample: Protecting sensitive information in task agnostic data release](https://mlsanity.com/paper/2203.13204/) (2022)
- [Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations](https://mlsanity.com/paper/2302.14242/) (2023)
- [Data Sharing and Compression for Cooperative Networked Control](https://mlsanity.com/paper/2109.14675/) (2021)
- [Task-Aware Network Coding Over Butterfly Network](https://mlsanity.com/paper/2201.11917/) (2022)
- [Differentially Private Timeseries Forecasts for Networked Control](https://mlsanity.com/paper/2210.00358/) (2022)

## Built on by (most cited first, 6 of 6)

- [CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features](https://mlsanity.com/paper/2410.07610/) (2024)
- [Any2Any: Incomplete Multimodal Retrieval with Conformal Prediction](https://mlsanity.com/paper/2411.10513/) (2024)
- [RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression](https://mlsanity.com/paper/2501.12216/) (2025)
- [Task and Perception-aware Distributed Source Coding for Correlated Speech under Bandwidth-constrained Channels](https://mlsanity.com/paper/2501.17879/) (2025)
- [Stabilization of Perturbed Loss Function: Differential Privacy without Gradient Noise](https://mlsanity.com/paper/2508.15523/) (2025)
- [SSR: A Generic Framework for Text-Aided Map Compression for Localization](https://mlsanity.com/paper/2603.04272/) (2026)

## Abstract (arXiv)

Efficient compression of correlated data is essential to minimize communication overload in multi-sensor networks. In such networks, each sensor independently compresses the data and transmits them to a central node due to limited communication bandwidth. A decoder at the central node decompresses and passes the data to a pre-trained machine learning-based task to generate the final output. Thus, it is important to compress the features that are relevant to the task. Additionally, the final performance depends heavily on the total available bandwidth. In practice, it is common to encounter varying availability in bandwidth, and higher bandwidth results in better performance of the task. We design a novel distributed compression framework composed of independent encoders and a joint decoder, which we call neural distributed principal component analysis (NDPCA). NDPCA flexibly compresses data from multiple sources to any available bandwidth with a single model, reducing computing and storage overhead. NDPCA achieves this by learning low-rank task representations and efficiently distributing bandwidth among sensors, thus providing a graceful trade-off between performance and bandwidth. Experiments show that NDPCA improves the success rate of multi-view robotic arm manipulation by 9% and the accuracy of object detection tasks on satellite imagery by 14% compared to an autoencoder with uniform bandwidth allocation.