TensorLog: A Probabilistic Database Implemented Using Deep-Learning Infrastructure

Abstract

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. The integration with these frameworks enables use of GPU-based parallel processors for inference and learning, making TensorLog the first highly parallellizable probabilistic logic. Experimental results show that TensorLog scales to problems involving hundreds of thousands of knowledge-base triples and tens of thousands of examples.

Cite

Text

Cohen et al. "TensorLog: A Probabilistic Database Implemented Using Deep-Learning Infrastructure." Journal of Artificial Intelligence Research, 2020. doi:10.1613/JAIR.1.11944

Markdown

[Cohen et al. "TensorLog: A Probabilistic Database Implemented Using Deep-Learning Infrastructure." Journal of Artificial Intelligence Research, 2020.](https://mlanthology.org/jair/2020/cohen2020jair-tensorlog/) doi:10.1613/JAIR.1.11944

BibTeX

@article{cohen2020jair-tensorlog,
  title     = {{TensorLog: A Probabilistic Database Implemented Using Deep-Learning Infrastructure}},
  author    = {Cohen, William W. and Yang, Fan and Mazaitis, Kathryn},
  journal   = {Journal of Artificial Intelligence Research},
  year      = {2020},
  pages     = {285-325},
  doi       = {10.1613/JAIR.1.11944},
  volume    = {67},
  url       = {https://mlanthology.org/jair/2020/cohen2020jair-tensorlog/}
}