TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs

2024-02-19

International Conference on Learning Representations

AI Summary

To address challenges in temporal knowledge graph (TKG) reasoning—including difficulty in learning logical rules, weak interpretability, poor generalization under low-resource conditions, and limited cross-temporal adaptability—this paper proposes the first differentiable temporal logical rule learning framework. Methodologically, it innovatively introduces temporal operators and constrained random walks to jointly model fine-grained dynamic patterns such as recurrence, temporal ordering, relational intervals, and duration. It integrates differentiable logic programming, path-based rule induction, and temporal embedding modeling. Evaluated on two standard benchmarks, the framework achieves significant improvements over state-of-the-art methods. It demonstrates strong robustness in few-shot learning, biased data, and train-inference temporal shift scenarios. Crucially, the induced rules attain both high predictive accuracy and clear semantic interpretability, enabling transparent, human-understandable reasoning over evolving knowledge.

Technology Category

Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal ReasoningPlanning, Routing, and Scheduling: Temporal PlanningData Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSemantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologiesSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Compared with static knowledge graphs, temporal knowledge graphs (tKG), which can capture the evolution and change of information over time, are more realistic and general. However, due to the complexity that the notion of time introduces to the learning of the rules, an accurate graph reasoning, e.g., predicting new links between entities, is still a difficult problem. In this paper, we propose TILP, a differentiable framework for temporal logical rules learning. By designing a constrained random walk mechanism and the introduction of temporal operators, we ensure the efficiency of our model. We present temporal features modeling in tKG, e.g., recurrence, temporal order, interval between pair of relations, and duration, and incorporate it into our learning process. We compare TILP with state-of-the-art methods on two benchmark datasets. We show that our proposed framework can improve upon the performance of baseline methods while providing interpretable results. In particular, we consider various scenarios in which training samples are limited, data is biased, and the time range between training and inference are different. In all these cases, TILP works much better than the state-of-the-art methods.

Problem

• Learning temporal logical rules on knowledge graphs
• Predicting new links between entities over time
• Handling limited, biased data and varying time ranges

Innovation

• Differentiable framework for temporal logical rules
• Constrained random walk with temporal operators
• Temporal features modeling in knowledge graphs