Distributed and Rate-Adaptive Feature Compression
This work addresses communication efficiency for distributed sensor networks in inference tasks, but it is incremental as it builds on existing compression methods with adaptive enhancements.
The paper tackles the problem of compressing features from distributed sensors for linear regression under varying communication constraints, proposing a scheme that quantizes one-dimensional projections and adapts to rate changes, with effectiveness demonstrated through simulated experiments.
We study the problem of distributed and rate-adaptive feature compression for linear regression. A set of distributed sensors collect disjoint features of regressor data. A fusion center is assumed to contain a pretrained linear regression model, trained on a dataset of the entire uncompressed data. At inference time, the sensors compress their observations and send them to the fusion center through communication-constrained channels, whose rates can change with time. Our goal is to design a feature compression {scheme} that can adapt to the varying communication constraints, while maximizing the inference performance at the fusion center. We first obtain the form of optimal quantizers assuming knowledge of underlying regressor data distribution. Under a practically reasonable approximation, we then propose a distributed compression scheme which works by quantizing a one-dimensional projection of the sensor data. We also propose a simple adaptive scheme for handling changes in communication constraints. We demonstrate the effectiveness of the distributed adaptive compression scheme through simulated experiments.