# TensorLog: Deep Learning Meets Probabilistic DBs

arXiv: https://arxiv.org/abs/1707.05390 · HTML: https://mlsanity.com/paper/1707.05390/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2017.

## Built on by (most cited first, 11 of 11)

- [Scallop: A Language for Neurosymbolic Programming](https://mlsanity.com/paper/2304.04812/) (2023)
- [SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning](https://mlsanity.com/paper/2110.14266/) (2021)
- [Start from Zero: Triple Set Prediction for Automatic Knowledge Graph Completion](https://mlsanity.com/paper/2406.18166/) (2024)
- [RulE: Knowledge Graph Reasoning with Rule Embedding](https://mlsanity.com/paper/2210.14905/) (2022)
- [NeuroStrata: Harnessing Neurosymbolic Paradigms for Improved Design, Testability, and Verifiability of Autonomous CPS](https://mlsanity.com/paper/2502.12267/) (2025)
- [Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming](https://mlsanity.com/paper/2503.21937/) (2025)
- [NeuralLog: a Neural Logic Language](https://mlsanity.com/paper/2105.01442/) (2021)
- [Logical Boltzmann Machines](https://mlsanity.com/paper/2112.05841/) (2021)
- [Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysis](https://mlsanity.com/paper/2509.07122/) (2025)
- [Reasoning in Neurosymbolic AI](https://mlsanity.com/paper/2505.20313/) (2025)
- [SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2510.00279/) (2025)

## Abstract (arXiv)

We present an implementation of a probabilistic first-order logic called TensorLog, in which classes of logical queries are compiled into differentiable functions in a neural-network infrastructure such as Tensorflow or Theano. This leads to a close integration of probabilistic logical reasoning with deep-learning infrastructure: in particular, it enables high-performance deep learning frameworks to be used for tuning the parameters of a probabilistic logic. Experimental results show that TensorLog scales to problems involving hundreds of thousands of knowledge-base triples and tens of thousands of examples.