Analyzing Differentiable Fuzzy Implications

Emile van Krieken, Erman Acar, Frank van Harmelen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Combining symbolic and neural approaches has gained considerable attention in the AI community, as it is often argued that the strengths and weaknesses of these approaches are complementary. One such trend in the literature are weakly supervised learning techniques that employ operators from fuzzy logics. In particular, they use prior background knowledge described in such logics to help the training of a neural network from unlabeled and noisy data. By interpreting logical symbols using neural networks (or grounding them), this background knowledge can be added to regular loss functions, hence making reasoning a part of learning. In this paper, we investigate how implications from the fuzzy logic literature behave in a differentiable setting. In such a setting, we analyze the differences between the formal properties of these fuzzy implications. It turns out that various fuzzy implications, including some of the most well-known, are highly unsuitable for use in a differentiable learning setting. A further finding shows a strong imbalance between gradients driven by the antecedent and the consequent of the implication. Furthermore, we introduce a new family of fuzzy implications (called sigmoidal implications) to tackle this phenomenon. Finally, we empirically show that it is possible to use Differentiable Fuzzy Logics for semi-supervised learning, and show that sigmoidal implications outperform other choices of fuzzy implications.
Original languageEnglish
Title of host publicationProceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning (KR 2020) Special Session on KR and Machine Learning
EditorsDigo Calvanese, Esra Erdem, Michael Thielscher
PublisherIJCAI Organization
Pages893-903
Number of pages11
ISBN (Electronic)9780999241172
DOIs
Publication statusPublished - 18 Sept 2020
Event17th International Conference on Principles of Knowledge Representation and Reasoning - Rhodes, Greece
Duration: 12 Sept 202018 Sept 2020
https://kr2020.inf.unibz.it/

Publication series

NameKR Proceedings: Conference on Principles of Knowledge Representation and Reasoning
PublisherIJCAI Organization
ISSN (Electronic)2334-1033

Conference

Conference17th International Conference on Principles of Knowledge Representation and Reasoning
Abbreviated titleKR 2020
Country/TerritoryGreece
CityRhodes
Period12/09/2018/09/20
Internet address

Fingerprint

Dive into the research topics of 'Analyzing Differentiable Fuzzy Implications'. Together they form a unique fingerprint.

Cite this