Knowledge Tree
Inductive Logic Programming (ILP)
Also known as: ILP, inductive logic programming (ILP), Inductive Logic Programming
Facts (10)
Sources
Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org Nov 7, 2024 7 facts
claimLogical Neural Networks (LNN) applied in the Inductive Logic Programming (ILP) direction allow systems to handle complexity and uncertainty in real-world data while improving learning efficiency and the quality of rules.
referenceFinzel et al. (2022) proposed a method using Graph Neural Networks (GNN) to classify relational data, verifying outputs by generating explanations combined with Inductive Logic Programming (ILP).
claimThe intermediate representation combining latent vector embeddings and Prolog rules is partially explicit, and the decision-making logic involving neural network-learned features as input for Inductive Logic Programming (ILP) is partially explainable.
claimInductive Logic Programming (ILP) uses transformed symbolic data as background knowledge to learn rules that describe the logic of Graph Neural Network (GNN) classification decisions.
procedureThe intermediate representation method for Graph Neural Networks (GNNs) converts neural network output into Prolog facts and rules suitable for Inductive Logic Programming (ILP) processing, effectively bridging neural network features and symbolic logic.
referenceSen et al. (2022) proposed an LNN-based inductive logic programming method that learns interpretable logic rules from noisy, real-world data by generating rules as output based on structured input data.
claimRules generated by Inductive Logic Programming (ILP) for Graph Neural Network (GNN) classification decisions consider structural features, such as spatial relationships between nodes and node attributes like color and shape, alongside feature importance scores.
Papers - Dr Vaishak Belle vaishakbelle.github.io 1 fact
referenceThe paper 'Deep Inductive Logic Programming meets Reinforcement Learning' by A. Bueff and V. Belle was published in the ICLP proceedings in 2023.
Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org Feb 16, 2025 1 fact
procedureThe detect-understand-act (DUA) framework operates in three stages: the detect module uses computer vision to process unstructured data into symbolic representations; the understand component uses answer set programming (ASP) and inductive logic programming (ILP) to ensure decisions align with symbolic rules; and the act component uses pre-trained reinforcement learning policies to refine symbolic representations.
Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org 1 fact
claimMachine learning approaches to ontology learning include statistic-based methods, such as co-occurrence analysis and clustering, and logic-based approaches, such as inductive logic programming or logical inference.