Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations

no code implementations • 12 Mar 2024 • Harish G. Naik, Jan Polster, Raj Shekhar, Tamás Horváth, György Turán

EEGL is an iterative self-improving algorithm, which starts with a learned "vanilla" GNN, and repeatedly uses frequent subgraph mining to find relevant patterns in explanation subgraphs.

Graph Learning Node Classification

Explanation from Specification

no code implementations • 13 Dec 2020 • Harish Naik, György Turán

We formulate an approach where the type of explanation produced is guided by a specification.

Explainable Artificial Intelligence (XAI) Philosophy

Measuring an Artificial Intelligence System's Performance on a Verbal IQ Test For Young Children

no code implementations • 11 Sep 2015 • Stellan Ohlsson, Robert H. Sloan, György Turán, Aaron Urasky

The large variations among subtests and ordinary common sense strongly suggest that the WPPSI-III VIQ results do not show that "ConceptNet has the verbal abilities a four-year-old."

Common Sense Reasoning Question Answering