Refining neural network predictions using background knowledge

06/10/2022
by   Alessandro Daniele, et al.
0

Recent work has shown logical background knowledge can be used in learning systems to compensate for a lack of labeled training data. Many methods work by creating a loss function that encodes this knowledge. However, often the logic is discarded after training, even if it is still useful at test time. Instead, we ensure neural network predictions satisfy the knowledge by refining the predictions with an extra computation step. We introduce differentiable refinement functions that find a corrected prediction close to the original prediction. We study how to effectively and efficiently compute these refinement functions. Using a new algorithm called Iterative Local Refinement (ILR), we combine refinement functions to find refined predictions for logical formulas of any complexity. ILR finds refinements on complex SAT formulas in significantly fewer iterations and frequently finds solutions where gradient descent can not. Finally, ILR produces competitive results in the MNIST addition task.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/10/2023

Injecting Logical Constraints into Neural Networks via Straight-Through Estimators

Injecting discrete logical constraints into neural network learning is o...
research
08/22/2017

Anytime Neural Network: a Versatile Trade-off Between Computation and Accuracy

Anytime predictors first produce crude results quickly, and then continu...
research
05/18/2018

Trusted Neural Networks for Safety-Constrained Autonomous Control

We propose Trusted Neural Network (TNN) models, which are deep neural ne...
research
05/31/2022

Knowledge Enhanced Neural Networks for relational domains

In the recent past, there has been a growing interest in Neural-Symbolic...
research
05/24/2017

Logic Tensor Networks for Semantic Image Interpretation

Semantic Image Interpretation (SII) is the task of extracting structured...
research
12/16/2021

Constraint-based graph network simulator

In the rapidly advancing area of learned physical simulators, nearly all...

Please sign up or login with your details

Forgot password? Click here to reset