Saved in:
Bibliographic Details
Main Authors: Ahmed, Kareem, Teso, Stefano, Morettin, Paolo, Di Liello, Luca, Ardino, Pierfrancesco, Gobbi, Jacopo, Liang, Yitao, Wang, Eric, Chang, Kai-Wei, Passerini, Andrea, Broeck, Guy Van den
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.07387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916243585368064
author Ahmed, Kareem
Teso, Stefano
Morettin, Paolo
Di Liello, Luca
Ardino, Pierfrancesco
Gobbi, Jacopo
Liang, Yitao
Wang, Eric
Chang, Kai-Wei
Passerini, Andrea
Broeck, Guy Van den
author_facet Ahmed, Kareem
Teso, Stefano
Morettin, Paolo
Di Liello, Luca
Ardino, Pierfrancesco
Gobbi, Jacopo
Liang, Yitao
Wang, Eric
Chang, Kai-Wei
Passerini, Andrea
Broeck, Guy Van den
contents Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the independence of the outputs. These outputs, however, jointly encode an object, e.g. a path in a graph, and are therefore related through the structure underlying the output space. We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training by minimizing the network's violation of such dependencies, steering the network towards predicting distributions satisfying the underlying structure. At the same time, it is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby, while also enabling efficient end-to-end training and inference. We also discuss key improvements and applications of the semantic loss. One limitations of the semantic loss is that it does not exploit the association of every data point with certain features certifying its membership in a target class. We should therefore prefer minimum-entropy distributions over valid structures, which we obtain by additionally minimizing the neuro-symbolic entropy. We empirically demonstrate the benefits of this more refined formulation. Moreover, the semantic loss is designed to be modular and can be combined with both discriminative and generative neural models. This is illustrated by integrating it into generative adversarial networks, yielding constrained adversarial networks, a novel class of deep generative models able to efficiently synthesize complex objects obeying the structure of the underlying domain.
format Preprint
id arxiv_https___arxiv_org_abs_2405_07387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Semantic Loss Functions for Neuro-Symbolic Structured Prediction
Ahmed, Kareem
Teso, Stefano
Morettin, Paolo
Di Liello, Luca
Ardino, Pierfrancesco
Gobbi, Jacopo
Liang, Yitao
Wang, Eric
Chang, Kai-Wei
Passerini, Andrea
Broeck, Guy Van den
Machine Learning
Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the independence of the outputs. These outputs, however, jointly encode an object, e.g. a path in a graph, and are therefore related through the structure underlying the output space. We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training by minimizing the network's violation of such dependencies, steering the network towards predicting distributions satisfying the underlying structure. At the same time, it is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby, while also enabling efficient end-to-end training and inference. We also discuss key improvements and applications of the semantic loss. One limitations of the semantic loss is that it does not exploit the association of every data point with certain features certifying its membership in a target class. We should therefore prefer minimum-entropy distributions over valid structures, which we obtain by additionally minimizing the neuro-symbolic entropy. We empirically demonstrate the benefits of this more refined formulation. Moreover, the semantic loss is designed to be modular and can be combined with both discriminative and generative neural models. This is illustrated by integrating it into generative adversarial networks, yielding constrained adversarial networks, a novel class of deep generative models able to efficiently synthesize complex objects obeying the structure of the underlying domain.
title Semantic Loss Functions for Neuro-Symbolic Structured Prediction
topic Machine Learning
url https://arxiv.org/abs/2405.07387