SEFA, a supervised latent-variable model with stochastic encoders and a gradient-based acquisition score, outperforms RL and mutual-information baselines on active feature acquisition benchmarks.
The train set is size 60,000, and the validation and test sets are both size 10,000
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Stochastic Encodings for Active Feature Acquisition
SEFA, a supervised latent-variable model with stochastic encoders and a gradient-based acquisition score, outperforms RL and mutual-information baselines on active feature acquisition benchmarks.