Variable Assignment Invariant Neural Networks for Learning Logic Programs
This work addresses the challenge of learning logic programs for symbolic AI, offering a solution to noise and generalization issues, though it appears incremental by building on existing frameworks.
The paper tackles the problem of learning logic programs from state transitions by introducing a neural network technique that enforces variable assignment invariance, addressing issues like noise handling and generalization in existing symbolic and neural methods. The method demonstrates effectiveness and scalability across various experiments.
Learning from interpretation transition (LFIT) is a framework for learning rules from observed state transitions. LFIT has been implemented in purely symbolic algorithms, but they are unable to deal with noise or generalize to unobserved transitions. Rule extraction based neural network methods suffer from overfitting, while more general implementation that categorize rules suffer from combinatorial explosion. In this paper, we introduce a technique to leverage variable permutation invariance inherent in symbolic domains. Our technique ensures that the permutation and the naming of the variables would not affect the results. We demonstrate the effectiveness and the scalability of this method with various experiments. Our code is publicly available at https://github.com/phuayj/delta-lfit-2