# A Scalable Technique for Weak-Supervised Learning with Domain Constraints

arXiv: https://arxiv.org/abs/2301.05253 · HTML: https://mlsanity.com/paper/2301.05253/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 12 Jan 2023.

## Builds on (most cited first, 7 of 7)

- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [A Rewriting System for Convex Optimization Problems](https://mlsanity.com/paper/1709.04494/) (2017)
- [Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning](https://mlsanity.com/paper/2006.06649/) (2020)
- [DeepStochLog: Neural Stochastic Logic Programming](https://mlsanity.com/paper/2106.12574/) (2021)
- [Beyond the Grounding Bottleneck: Datalog Techniques for Inference in Probabilistic Logic Programs (Technical Report)](https://mlsanity.com/paper/1911.07750/) (2019)
- [Counting Query Answers over a DL-Lite Knowledge Base (extended version)](https://mlsanity.com/paper/2005.05886/) (2020)

## Abstract (arXiv)

We propose a novel scalable end-to-end pipeline that uses symbolic domain knowledge as constraints for learning a neural network for classifying unlabeled data in a weak-supervised manner. Our approach is particularly well-suited for settings where the data consists of distinct groups (classes) that lends itself to clustering-friendly representation learning and the domain constraints can be reformulated for use of efficient mathematical optimization techniques by considering multiple training examples at once. We evaluate our approach on a variant of the MNIST image classification problem where a training example consists of image sequences and the sum of the numbers represented by the sequences, and show that our approach scales significantly better than previous approaches that rely on computing all constraint satisfying combinations for each training example.