REVIEW 3 cited by
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
read the original abstract
We develop BatchBALD, a tractable approximation to the mutual information between a batch of points and model parameters, which we use as an acquisition function to select multiple informative points jointly for the task of deep Bayesian active learning. BatchBALD is a greedy linear-time $1 - \frac{1}{e}$-approximate algorithm amenable to dynamic programming and efficient caching. We compare BatchBALD to the commonly used approach for batch data acquisition and find that the current approach acquires similar and redundant points, sometimes performing worse than randomly acquiring data. We finish by showing that, using BatchBALD to consider dependencies within an acquisition batch, we achieve new state of the art performance on standard benchmarks, providing substantial data efficiency improvements in batch acquisition.
Forward citations
Cited by 3 Pith papers
-
AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing
AURA is an adaptive uncertainty-aware refinement method for auditing LLM-as-a-judge pairwise decisions that learns human-consistency signals through selective human verification on uncertain cases.
-
Cognitive-Uncertainty Guided Knowledge Distillation for Accurate Classification of Student Misconceptions
A cognitive-uncertainty guided two-stage KD framework filters to 10.3% of samples to reach 0.9585 MAP@3 and 84.38% accuracy with a 4B model, beating larger LLMs on misconception classification.
-
Testing the Assumptions of Active Learning for Translation Tasks with Few Samples
Informativeness and diversity of samples selected by active learning show no correlation with test performance on translation tasks using few samples; ordering and pre-training effects dominate instead.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.