Is the Proof Length a Good Indicator of Hardness for Reason-able Embeddings?
[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee
2023
chapter in monograph / paper
english
- description logics
- reason-able embeddings
- transfer learning
- neural-symbolic reasoning
EN Reason-able embeddings are recently proposed embeddings for knowledge bases (KBs) in the description logic 𝒜ℒ𝒞 capable of casting multiple KBs into a single latent space using a transferable neural reasoner. While they exhibit remarkable performance on real-world KBs, it is so far unknown what are their exact limits. In this paper, we systematically investigate their performance using a set of synthetic KBs in the description logic ℰℒ, a subset of 𝒜ℒ𝒞. We use the proof length as a measure of reasoning complexity and present a random KB generator taking the proof length into account. We train the reason-able embeddings with and without transfer learning and investigate whether the complexity of the training set and the test set is related to the reasoning performance of the embeddings and their neural reasoner.
150 - 161
CC BY (attribution alone)
publisher's website
final published version
at the time of publication
5