Object-Oriented Transition Modeling with Inductive Logic Programming

2026-02-07

AI Summary

This work addresses the challenge of constructing world models that are generalizable, interpretable, and computationally efficient from observational data. To this end, the authors propose a novel approach that integrates object-oriented representations with inductive logic programming to learn symbolic, structured dynamics of the environment. By leveraging symbolic reasoning and compositional structure, the method achieves significantly stronger expressiveness and out-of-distribution generalization compared to existing neural baselines, setting new state-of-the-art results across multiple benchmark tasks. Ablation studies further confirm the contribution of each component, highlighting the method’s innovative synergy between symbolic reasoning and structured representation learning.

Technology Category

• Knowledge Representation and Reasoning: Logic Programming
• Computer Vision: Visual Reasoning & Symbolic Representations
• Machine Learning: Statistical Relational/Logic Learning

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Building models of the world from observation, i.e., induction, is one of the major challenges in machine learning. In order to be useful, models need to maintain accuracy when used in novel situations, i.e., generalize. In addition, they should be easy to interpret and efficient to train. Prior work has investigated these concepts in the context of object-oriented representations inspired by human cognition. In this paper, we develop a novel learning algorithm that is substantially more powerful than these previous methods. Our thorough experiments, including ablation tests and comparison with neural baselines, demonstrate a significant improvement over the state-of-the-art.

Problem

• induction
• object-oriented modeling
• generalization
• interpretability
• machine learning

Innovation

• Object-Oriented Modeling
• Inductive Logic Programming
• Generalization
• Interpretable AI
• State Transition Learning