Semi-Supervised Learning using Differentiable Reasoning

08/13/2019
by   Emile van Krieken, et al.
13

We introduce Differentiable Reasoning (DR), a novel semi-supervised learning technique which uses relational background knowledge to benefit from unlabeled data. We apply it to the Semantic Image Interpretation (SII) task and show that background knowledge provides significant improvement. We find that there is a strong but interesting imbalance between the contributions of updates from Modus Ponens (MP) and its logical equivalent Modus Tollens (MT) to the learning process, suggesting that our approach is very sensitive to a phenomenon called the Raven Paradox. We propose a solution to overcome this situation.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset