On the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors


Matteo Magnini, Giovanni Ciatto, Andrea Omicini

Proceedings of the 4th International Workshop on EXplainable and TRAnsparent AI and Multi-Agent Systems
 2022
Springer

A long-standing ambition in artificial intelligence is to integrate predictors' inductive features (i.e., learning from examples) with deductive capabilities (i.e., drawing inferences from prior symbolic knowledge). Many algorithms methods in the literature support injection of prior symbolic knowledge into predictors, generally following the purpose of attaining better (i.e., more effective or efficient w.r.t. predictive performance) predictors. However, to the best of our knowledge, running implementations of these algorithms are currently either proof of concepts or unavailable in most cases. Moreover, an unified, coherent software framework supporting them as well as their interchange, comparison and exploitation in arbitrary ML workflows is currently missing. Accordingly, in this paper we present PSyKI, a platform providing general-purpose support to symbolic knowledge injection into predictors via different algorithms.

(keywords) Symbolic Knowledge Injection,  Explainable AI, XAI, Neural Networks, PSyKI
 @inproceedings{PsykiExtraamas2022,
keywords = {Symbolic Knowledge Injection,  Explainable AI, XAI, Neural Networks, PSyKI},
year = 2022,
talk = {Talks.PsykiExtraamas2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
venue_e = {Events.Extraamas2022},
sort = {inproceedings},
publisher = {Springer},
status = {In press},
title = {On the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors},
booktitle = {Proceedings of the 4th International Workshop on EXplainable and TRAnsparent AI and Multi-Agent Systems },
abstract = {A long-standing ambition in artificial intelligence is to integrate predictors' inductive features (i.e., learning from examples) with deductive capabilities (i.e., drawing inferences from prior symbolic knowledge). Many algorithms methods in the literature support injection of prior symbolic knowledge into predictors, generally following the purpose of attaining better (i.e., more effective or efficient w.r.t. predictive performance) predictors. However, to the best of our knowledge, running implementations of these algorithms are currently either proof of concepts or unavailable in most cases. Moreover, an unified, coherent software framework supporting them as well as their interchange, comparison and exploitation in arbitrary ML workflows is currently missing. Accordingly, in this paper we present PSyKI, a platform providing general-purpose support to symbolic knowledge injection into predictors via different algorithms.}

Talks

Events

  • EXplainable and TRAnsparent AI and Multi-Agent Systems: Fourth International Workshop (EXTRAAMAS 2022) — 09/05/2022–10/05/2022

Publication

— authors

Matteo Magnini, Giovanni Ciatto, Andrea Omicini

— status

in press

— sort

paper in proceedings

Venue

— volume

Proceedings of the 4th International Workshop on EXplainable and TRAnsparent AI and Multi-Agent Systems

— publication date

2022

BibTeX

— BibTeX ID
PsykiExtraamas2022
— BibTeX category
inproceedings

Partita IVA: 01131710376 - Copyright © 2008-2022 APICe@DISI Research Group - PRIVACY