# Batch Selection and Communication for Active Learning with Edge Labeling

arXiv: https://arxiv.org/abs/2311.08053 · HTML: https://mlsanity.com/paper/2311.08053/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Builds on (most cited first, 12 of 12)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [Few-shot Learning with Noisy Labels](https://mlsanity.com/paper/2204.05494/) (2022)
- [Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixup](https://mlsanity.com/paper/2012.09413/) (2020)
- [Wireless Federated Langevin Monte Carlo: Repurposing Channel Noise for Bayesian Sampling and Privacy](https://mlsanity.com/paper/2108.07644/) (2021)
- [Robust Active Distillation](https://mlsanity.com/paper/2210.01213/) (2022)
- [Distilling Calibrated Student from an Uncalibrated Teacher](https://mlsanity.com/paper/2302.11472/) (2023)

## Abstract (arXiv)

Conventional retransmission (ARQ) protocols are designed with the goal of ensuring the correct reception of all the individual transmitter's packets at the receiver. When the transmitter is a learner communicating with a teacher, this goal is at odds with the actual aim of the learner, which is that of eliciting the most relevant label information from the teacher. Taking an active learning perspective, this paper addresses the following key protocol design questions: (i) Active batch selection: Which batch of inputs should be sent to the teacher to acquire the most useful information and thus reduce the number of required communication rounds? (ii) Batch encoding: Can batches of data points be combined to reduce the communication resources required at each communication round? Specifically, this work introduces Communication-Constrained Bayesian Active Knowledge Distillation (CC-BAKD), a novel protocol that integrates Bayesian active learning with compression via a linear mix-up mechanism. Comparisons with existing active learning protocols demonstrate the advantages of the proposed approach.