# Towards Foundation Model on Temporal Knowledge Graph Reasoning

arXiv: https://arxiv.org/abs/2506.06367 · HTML: https://mlsanity.com/paper/2506.06367/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [Inductive Relation Prediction by Subgraph Reasoning](https://mlsanity.com/paper/1911.06962/) (2019)
- [Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs](https://mlsanity.com/paper/1705.05742/) (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)
- [Question Answering Over Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.01515/) (2021)
- [Towards Foundation Models for Knowledge Graph Reasoning](https://mlsanity.com/paper/2310.04562/) (2023)
- [GFT: Graph Foundation Model with Transferable Tree Vocabulary](https://mlsanity.com/paper/2411.06070/) (2024)
- [TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2109.04101/) (2021)
- [TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs](https://mlsanity.com/paper/2112.08025/) (2021)
- [InGram: Inductive Knowledge Graph Embedding via Relation Graphs](https://mlsanity.com/paper/2305.19987/) (2023)
- [TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation](https://mlsanity.com/paper/2010.01029/) (2020)
- [Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning](https://mlsanity.com/paper/2305.10613/) (2023)
- [Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding](https://mlsanity.com/paper/2110.14170/) (2021)
- [Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2203.07782/) (2022)
- [GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models](https://mlsanity.com/paper/2310.07793/) (2023)
- [A Survey on Temporal Knowledge Graph: Representation Learning and Applications](https://mlsanity.com/paper/2403.04782/) (2024)
- [zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models](https://mlsanity.com/paper/2311.10112/) (2023)
- [Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2305.07912/) (2023)
- [HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces](https://mlsanity.com/paper/2312.13680/) (2023)
- [Incorporating Structured Sentences with Time-enhanced BERT for Fully-inductive Temporal Relation Prediction](https://mlsanity.com/paper/2304.04717/) (2023)
- [A Unified Temporal Knowledge Graph Reasoning Model Towards Interpolation and Extrapolation](https://mlsanity.com/paper/2405.18106/) (2024)
- [ECOLA: Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations](https://mlsanity.com/paper/2203.09590/) (2022)

## Built on by (most cited first, 3 of 3)

- [Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities](https://mlsanity.com/paper/2604.10164/) (2026)
- [AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2605.07121/) (2026)
- [Learning Across Temporal Graph Representation Silos](https://mlsanity.com/paper/2610.19576/) (2026)

## Abstract (arXiv)

Temporal Knowledge Graphs (TKGs) store temporal facts with quadruple formats (s, p, o, t). Existing Temporal Knowledge Graph Embedding (TKGE) models perform link prediction tasks in transductive or semi-inductive settings, which means the entities, relations, and temporal information in the test graph are fully or partially observed during training. Such reliance on seen elements during inference limits the models' ability to transfer to new domains and generalize to real-world scenarios. A central limitation is the difficulty in learning representations for entities, relations, and timestamps that are transferable and not tied to dataset-specific vocabularies. To overcome these limitations, we introduce the first fully-inductive approach to temporal knowledge graph link prediction. Our model employs sinusoidal positional encodings to capture fine-grained temporal patterns and generates adaptive entity and relation representations using message passing conditioned on both local and global temporal contexts. Our model design is agnostic to temporal granularity and time span, effectively addressing temporal discrepancies across TKGs and facilitating time-aware structural information transfer. As a pretrained, scalable, and transferable model, POSTRA demonstrates strong zero-shot performance on unseen temporal knowledge graphs, effectively generalizing to novel entities, relations, and timestamps. Extensive theoretical analysis and empirical results show that a single pretrained model can improve zero-shot performance on various inductive temporal reasoning scenarios, marking a significant step toward a foundation model for temporal KGs.