# TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs

arXiv: https://arxiv.org/abs/2402.12309 · HTML: https://mlsanity.com/paper/2402.12309/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 16 of 16)

- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [End-to-End Differentiable Proving](https://mlsanity.com/paper/1705.11040/) (2017)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [Tensor Decompositions for temporal knowledge base completion](https://mlsanity.com/paper/2004.04926/) (2020)
- [Diachronic Embedding for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1907.03143/) (2019)
- [Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning](https://mlsanity.com/paper/1903.08948/) (2019)
- [TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs](https://mlsanity.com/paper/2112.08025/) (2021)
- [NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language](https://mlsanity.com/paper/1906.06187/) (2019)
- [dynnode2vec: Scalable Dynamic Network Embedding](https://mlsanity.com/paper/1812.02356/) (2018)
- [Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols](https://mlsanity.com/paper/2005.05035/) (2020)
- [Inductive Logic Programming via Differentiable Deep Neural Logic Networks](https://mlsanity.com/paper/1906.03523/) (2019)
- [Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2004.04412/) (2020)
- [One-shot Learning for Temporal Knowledge Graphs](https://mlsanity.com/paper/2010.12144/) (2020)
- [Time-aware Graph Embedding: A temporal smoothness and task-oriented approach](https://mlsanity.com/paper/2007.11164/) (2020)

## Built on by (most cited first, 22 of 22)

- [DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literature](https://mlsanity.com/paper/2405.04819/) (2024)
- [Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2405.14170/) (2024)
- [Towards Rationality in Language and Multimodal Agents: A Survey](https://mlsanity.com/paper/2406.00252/) (2024)
- [TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.11460/) (2024)
- [FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference](https://mlsanity.com/paper/2410.20105/) (2024)
- [RealTCD: Temporal Causal Discovery from Interventional Data with Large Language Model](https://mlsanity.com/paper/2404.14786/) (2024)
- [SemanticFormer: Holistic and Semantic Traffic Scene Representation for Trajectory Prediction using Knowledge Graphs](https://mlsanity.com/paper/2404.19379/) (2024)
- [Automatic Knowledge Graph Construction for Judicial Cases](https://mlsanity.com/paper/2404.09416/) (2024)
- [Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction](https://mlsanity.com/paper/2408.07088/) (2024)
- [Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2405.10621/) (2024)
- [Advancing Prompt Recovery in NLP: A Deep Dive into the Integration of Gemma-2b-it and Phi2 Models](https://mlsanity.com/paper/2407.05233/) (2024)
- [DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion](https://mlsanity.com/paper/2507.11229/) (2025)
- [TransTARec: Time-Adaptive Translating Embedding Model for Next POI Recommendation](https://mlsanity.com/paper/2404.07096/) (2024)
- [Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities](https://mlsanity.com/paper/2604.10164/) (2026)
- [Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2501.00252/) (2024)
- [Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge Graphs](https://mlsanity.com/paper/2505.12788/) (2025)
- [CountTRuCoLa: Rule Learning for Interpretable Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2509.09474/) (2025)
- [Beyond Known Facts: Generating Unseen Temporal Knowledge to Address Data Contamination in LLM Evaluation](https://mlsanity.com/paper/2601.13658/) (2026)
- [ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs](https://mlsanity.com/paper/2602.02382/) (2026)
- [Logi-PAR: Logic-Infused Patient Activity Recognition via Differentiable Rule](https://mlsanity.com/paper/2603.05184/) (2026)
- [AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2605.07121/) (2026)
- [From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphs](https://mlsanity.com/paper/2609.11170/) (2026)

## Abstract (arXiv)

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.