On the Design of PSyKE: A Platform for Symbolic Knowledge Extraction


pagemagnifierBibTeX_logo.pngmagnifierpage_white_acrobatmagnifier

Federico Sabbatini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini

Roberta Calegari, Giovanni Ciatto, Enrico Denti, Andrea Omicini, Giovanni Sartor (eds.)
“WOA 2021 – 22nd Workshop “From Objects to Agents””, pages 29–48
CEUR Workshop Proceedings (AI*IA Series) 2963
Sun SITE Central Europe, RWTH Aachen University
October 2021

A common practice in modern explainable AI is to post-hoc explain black-box machine learning (ML) predictors – such as neural networks – by extracting symbolic knowledge out of them, in the form of either rule lists or decision trees. By acting as a surrogate model, the extracted knowledge aims at revealing the inner working of the black box, thus enabling its inspection, representation, and explanation.
Various knowledge-extraction algorithms have been presented in the literature so far. Unfortunately, running implementations of most of them are currently either proof of concepts or unavailable. In any case, a unified, coherent software framework supporting them all – as well as their interchange, comparison, and exploitation in arbitrary ML workflows – is currently missing.
Accordingly, in this paper we present the design of PSyKE, a platform providing general-purpose support to symbolic knowledge extraction from different sorts of black-box predictors via many extraction algorithms. Notably, PSyKE targets the extraction of symbolic knowledge in logic form, making it possible to extract first-order logic clauses as output. The extracted knowledge is thus both machine- and human- interpretable, and it can be used as a starting point for further symbolic processing—e.g. automated reasoning.

(keywords) explainable AI, knowledge extraction, interpretable prediction, PSyKE

Talks

Events

  • 22nd Workshop “From Objects to Agents” (WOA 2021) — 01/09/2021–03/09/2021

Publications

Publication

— authors

— editors

— status

published

— sort

paper in proceedings

— publication date

October 2021

— volume

WOA 2021 – 22nd Workshop “From Objects to Agents”

— series

CEUR Workshop Proceedings / AI*IA Series

— volume

2963

— pages

29–48

— article no.

3

— number of pages

20

URLs

original page

identifiers

— DBLP

conf/woa/SabbatiniCCO21

— IRIS

11585/834364

— Scholar

879185583484020388

— Scopus

2-s2.0-85116894019

— print ISSN

1613-0073

Partita IVA: 01131710376 — Copyright © 2008–2023 APICe@DISI – PRIVACY