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. |
Year | Venue | Keywords |
---|---|---|
2022 | AAAI Conference on Artificial Intelligence | Machine Learning (ML),Knowledge Representation And Reasoning (KRR),Humans And AI (HAI),Data Mining & Knowledge Management (DMKM) |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Prithviraj Sen | 1 | 837 | 38.24 |
Breno W. S. R. de Carvalho | 2 | 0 | 0.34 |
Ryan Riegel | 3 | 2 | 1.09 |
Alexander G. Gray | 4 | 990 | 80.16 |