# Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities

arXiv: https://arxiv.org/abs/2604.10164 · HTML: https://mlsanity.com/paper/2604.10164/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 48 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning](https://mlsanity.com/paper/2305.10613/) (2023)
- [TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs](https://mlsanity.com/paper/2402.12309/) (2024)
- [Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs](https://mlsanity.com/paper/1904.05530/) (2019)
- [Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2305.07912/) (2023)
- [Towards Foundation Model on Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2506.06367/) (2025)

## Built on by (most cited first, 1 of 1)

- [Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle](https://mlsanity.com/paper/2605.13021/) (2026)

## Abstract (arXiv)

Reasoning on Temporal Knowledge Graphs (TKGs) is essential for predicting future events and time-aware facts. While existing methods are effective at capturing relational dynamics, their performance is limited by a closed-world assumption, which fails to account for emerging entities not present in the training. Notably, these entities continuously join the network without historical interactions. Empirical study reveals that emerging entities are widespread in TKGs, comprising roughly 25% of all entities. The absence of historical interactions of these entities leads to significant performance degradation in reasoning tasks. Whereas, we observe that entities with semantic similarities often exhibit comparable interaction histories, suggesting the presence of transferable temporal patterns. Inspired by this insight, we propose TransFIR (Transferable Inductive Reasoning), a novel framework that leverages historical interaction sequences from semantically similar known entities to support inductive reasoning. Specifically, we propose a codebook-based classifier that categorizes emerging entities into latent semantic clusters, allowing them to adopt reasoning patterns from similar entities. Experimental results demonstrate that TransFIR outperforms all baselines in reasoning on emerging entities, achieving an average improvement of 28.6% in Mean Reciprocal Rank (MRR) across multiple datasets. The implementations are available at https://github.com/zhaodazhuang2333/TransFIR.