Timezone: »

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

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.

Author Information

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

More from the Same Authors