Differentiable Learning of Logical Rules for Knowledge Base Reasoning
نویسندگان
چکیده
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.
منابع مشابه
Differentiable Learning of Logical Rules for Knowledge Base Completion
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 ...
متن کاملExtending the Qualitative Trajectory Calculus Based on the Concept of Accessibility of Moving Objects in the Paths
Qualitative spatial representation and reasoning are among the important capabilities in intelligent geospatial information system development. Although a large contribution to the study of moving objects has been attributed to the quantitative use and analysis of data, such calculations are ineffective when there is little inaccurate data on position and geometry or when explicitly explaining ...
متن کاملLearning Knowledge Base Inference with Neural Theorem Provers
In this paper we present a proof-of-concept implementation of Neural Theorem Provers (NTPs), end-to-end differentiable counterparts of discrete theorem provers that perform first-order inference on vector representations of symbols using function-free, possibly parameterized, rules. As such, NTPs follow a long tradition of neural-symbolic approaches to automated knowledge base inference, but di...
متن کاملA Framework for Learning and Inference in Network Management
This paper presents a network management framework which builds the management information infrastructure and equips the management applications with learning and reasoning abilities for automatic and adaptive management tasks. Views are global virtual management information constructed via logical rules from the distributed physical management information. Through these views, management appli...
متن کاملTensorLog: Deep Learning Meets Probabilistic DBs
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 neuralnetwork 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 framework...
متن کامل