Proceedings:
No. 8: AAAI-22 Technical Tracks 8
Volume
Issue:
Proceedings of the AAAI Conference on Artificial Intelligence, 36
Track:
AAAI Technical Track on Machine Learning III
Downloads:
Abstract:
Recent work on neuro-symbolic inductive logic programming has led to promising approaches that can learn explanatory rules from noisy, real-world data. While some proposals approximate logical operators with differentiable operators from fuzzy or real-valued logic that are parameter-free thus diminishing their capacity to fit the data, other approaches are only loosely based on logic making it difficult to interpret the learned ``rules". In this paper, we propose learning rules with the recently proposed logical neural networks (LNN). Compared to others, LNNs offer a strong connection to classical Boolean logic thus allowing for precise interpretation of learned rules while harboring parameters that can be trained with gradient-based optimization to effectively fit the data. We extend LNNs to induce rules in first-order logic. Our experiments on standard benchmarking tasks confirm that LNN rules are highly interpretable and can achieve comparable or higher accuracy due to their flexible parameterization.
DOI:
10.1609/aaai.v36i8.20795
AAAI
Proceedings of the AAAI Conference on Artificial Intelligence, 36