Timezone: »

 
Poster
Differentiable Learning of Logical Rules for Knowledge Base Reasoning
Fan Yang · Zhilin Yang · William Cohen

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #126
in Posters Mon »

We study the problem of learning probabilistic first-order logical rules for knowledge base reasoning. This learning problem is difficult because it requires learning the parameters in a continuous space as well as the structure in a discrete space. We propose a framework, Neural Logic Programming, that combines the parameter and structure learning of first-order logical rules in an end-to-end differentiable model. This approach is inspired by a recently-developed differentiable logic called TensorLog [5], where inference tasks can be compiled into sequences of differentiable operations. We design a neural controller system that learns to compose these operations. Empirically, our method outperforms prior work on multiple knowledge base benchmark datasets, including Freebase and WikiMovies.

Keywords: Program Induction · Neural Abstract Machines
[ Code]  [ Paper]  [ Poster] 

Author Information

Fan Yang (Carnegie Mellon University)
Zhilin Yang (Carnegie Mellon University)
William Cohen (Google AI)

More from the Same Authors