# Semi-Supervised Learning with Declaratively Specified Entropy Constraints

arXiv: https://arxiv.org/abs/1804.09238 · HTML: https://mlsanity.com/paper/1804.09238/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2018.

## Built on by (most cited first, 1 of 1)

- [An information-Theoretic Approach to Semi-supervised Transfer Learning](https://mlsanity.com/paper/2306.06731/) (2023)

## Abstract (arXiv)

We propose a technique for declaratively specifying strategies for semi-supervised learning (SSL). The proposed method can be used to specify ensembles of semi-supervised learning, as well as agreement constraints and entropic regularization constraints between these learners, and can be used to model both well-known heuristics such as co-training and novel domain-specific heuristics. In addition to representing individual SSL heuristics, we show that multiple heuristics can also be automatically combined using Bayesian optimization methods. We show consistent improvements on a suite of well-studied SSL benchmarks, including a new state-of-the-art result on a difficult relation extraction task.