Differentiable Inductive Logic Programming for Structured Examples

03/02/2021
by   Hikaru Shindo, et al.
0

The differentiable implementation of logic yields a seamless combination of symbolic reasoning and deep neural networks. Recent research, which has developed a differentiable framework to learn logic programs from examples, can even acquire reasonable solutions from noisy datasets. However, this framework severely limits expressions for solutions, e.g., no function symbols are allowed, and the shapes of clauses are fixed. As a result, the framework cannot deal with structured examples. Therefore we propose a new framework to learn logic programs from noisy and structured examples, including the following contributions. First, we propose an adaptive clause search method by looking through structured space, which is defined by the generality of the clauses, to yield an efficient search space for differentiable solvers. Second, we propose for ground atoms an enumeration algorithm, which determines a necessary and sufficient set of ground atoms to perform differentiable inference functions. Finally, we propose a new method to compose logic programs softly, enabling the system to deal with complex programs consisting of several clauses. Our experiments show that our new framework can learn logic programs from noisy and structured examples, such as sequences or trees. Our framework can be scaled to deal with complex programs that consist of several clauses with function symbols.

READ FULL TEXT
research
08/25/2018

Inductive Learning of Answer Set Programs from Noisy Examples

In recent years, non-monotonic Inductive Logic Programming has received ...
research
06/08/2019

Inductive Logic Programming via Differentiable Deep Neural Logic Networks

We propose a novel paradigm for solving Inductive Logic Programming (ILP...
research
08/18/2023

Learning MDL logic programs from noisy data

Many inductive logic programming approaches struggle to learn programs f...
research
04/02/2019

Learning Algorithms via Neural Logic Networks

We propose a novel learning paradigm for Deep Neural Networks (DNN) by u...
research
08/13/2022

Differentiable Inductive Logic Programming in High-Dimensional Space

Synthesizing large logic programs through Inductive Logic Programming (I...
research
04/28/2022

Learning First-Order Rules with Differentiable Logic Program Semantics

Learning first-order logic programs (LPs) from relational facts which yi...
research
11/13/2017

Learning Explanatory Rules from Noisy Data

Artificial Neural Networks are powerful function approximators capable o...

Please sign up or login with your details

Forgot password? Click here to reset