Neuro-Symbolic Constraint Programming for Structured Prediction

03/31/2021
by   Paolo Dragone, et al.
0

We propose Nester, a method for injecting neural networks into constrained structured predictors. The job of the neural network(s) is to compute an initial, raw prediction that is compatible with the input data but does not necessarily satisfy the constraints. The structured predictor then builds a structure using a constraint solver that assembles and corrects the raw predictions in accordance with hard and soft constraints. In doing so, Nester takes advantage of the features of its two components: the neural network learns complex representations from low-level data while the constraint programming component reasons about the high-level properties of the prediction task. The entire architecture can be trained in an end-to-end fashion. An empirical evaluation on handwritten equation recognition shows that Nester achieves better performance than both the neural network and the constrained structured predictor on their own, especially when training examples are scarce, while scaling to more complex problems than other neuro-programming approaches. Nester proves especially useful to reduce errors at the semantic level of the problem, which is particularly challenging for neural network architectures.Sub

READ FULL TEXT

page 3

page 5

page 8

research
06/01/2022

Semantic Probabilistic Layers for Neuro-Symbolic Learning

We design a predictive layer for structured-output prediction (SOP) that...
research
07/15/2023

NeurASP: Embracing Neural Networks into Answer Set Programming

We present NeurASP, a simple extension of answer set programs by embraci...
research
11/29/2022

Neural Feature-Adaptation for Symbolic Predictions Using Pre-Training and Semantic Loss

We are interested in neurosymbolic systems consisting of a high-level sy...
research
05/19/2021

Physical Constraint Embedded Neural Networks for inference and noise regulation

Neural networks often require large amounts of data to generalize and ca...
research
12/16/2021

Constraint-based graph network simulator

In the rapidly advancing area of learned physical simulators, nearly all...
research
12/09/2020

NSL: Hybrid Interpretable Learning From Noisy Raw Data

Inductive Logic Programming (ILP) systems learn generalised, interpretab...
research
10/17/2022

A Solver-Free Framework for Scalable Learning in Neural ILP Architectures

There is a recent focus on designing architectures that have an Integer ...

Please sign up or login with your details

Forgot password? Click here to reset