# A Unified Temporal Knowledge Graph Reasoning Model Towards Interpolation and Extrapolation arXiv: https://arxiv.org/abs/2405.18106 ยท HTML: https://mlsanity.com/paper/2405.18106/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. - Builds on 26 of its 55 references that are in the map. - First posted on arXiv 28 May 2024. ## Placed in - LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/) ## Builds on (most cited first, 26 of 26) - [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017) - [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013) - [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017) - [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014) - [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016) - [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017) - [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019) - [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021) - [Canonical Tensor Decomposition for Knowledge Base Completion](https://mlsanity.com/paper/1806.07297/) (2018) - [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018) - [End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion](https://mlsanity.com/paper/1811.04441/) (2018) - [Tensor Decompositions for temporal knowledge base completion](https://mlsanity.com/paper/2004.04926/) (2020) - [Causal Attention for Interpretable and Generalizable Graph Classification](https://mlsanity.com/paper/2112.15089/) (2021) - [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021) - [Diachronic Embedding for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1907.03143/) (2019) - [Knowledge Graph Reasoning with Relational Digraph](https://mlsanity.com/paper/2108.06040/) (2021) - [Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks](https://mlsanity.com/paper/2012.08492/) (2020) - [Probabilistic Logic Neural Networks for Reasoning](https://mlsanity.com/paper/1906.08495/) (2019) - [TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2109.04101/) (2021) - [Temporal Knowledge Graph Forecasting with Neural ODE](https://mlsanity.com/paper/2101.05151/) (2021) - [TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs](https://mlsanity.com/paper/2112.08025/) (2021) - [Knowledge Graph Embedding with Iterative Guidance from Soft Rules](https://mlsanity.com/paper/1711.11231/) (2017) - [TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation](https://mlsanity.com/paper/2010.01029/) (2020) - [Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols](https://mlsanity.com/paper/2005.05035/) (2020) - [Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition](https://mlsanity.com/paper/1911.07893/) (2019) - [Logic Rules Powered Knowledge Graph Embedding](https://mlsanity.com/paper/1903.03772/) (2019) ## Built on by (most cited first, 9 of 9) - [TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG](https://mlsanity.com/paper/2412.05447/) (2024) - [Towards Foundation Model on Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2506.06367/) (2025) - [VITA: Versatile Time Representation Learning for Temporal Hyper-Relational Knowledge Graphs](https://mlsanity.com/paper/2505.11803/) (2025) - [CountTRuCoLa: Rule Learning for Interpretable Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2509.09474/) (2025) - [TKGB: A Comprehensive Benchmark for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2602.08353/) (2026) - [MA-DAR: Manifold-Aligned Dynamic Adaptive Routing for Continual Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2607.21949/) (2026) - [GTIN: A Unified Framework for Joint Event and Time Prediction in Temporal Graphs](https://mlsanity.com/paper/2607.23556/) (2026) - [BridgeMem: Causal Dyadic Transition Residuals for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2609.29268/) (2026) - [CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference](https://mlsanity.com/paper/2609.36689/) (2026) ## Abstract (arXiv) Temporal knowledge graph (TKG) reasoning has two settings: interpolation reasoning and extrapolation reasoning. Both of them draw plenty of research interest and have great significance. Methods of the former de-emphasize the temporal correlations among facts sequences, while methods of the latter require strict chronological order of knowledge and ignore inferring clues provided by missing facts of the past. These limit the practicability of TKG applications as almost all of the existing TKG reasoning methods are designed specifically to address either one setting. To this end, this paper proposes an original Temporal PAth-based Reasoning (TPAR) model for both the interpolation and extrapolation reasoning. TPAR performs a neural-driven symbolic reasoning fashion that is robust to ambiguous and noisy temporal data and with fine interpretability as well. Comprehensive experiments show that TPAR outperforms SOTA methods on the link prediction task for both the interpolation and the extrapolation settings. A novel pipeline experimental setting is designed to evaluate the performances of SOTA combinations and the proposed TPAR towards interpolation and extrapolation reasoning. More diverse experiments are conducted to show the robustness and interpretability of TPAR.