# DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization

arXiv: https://arxiv.org/abs/2512.12669 · HTML: https://mlsanity.com/paper/2512.12669/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [Temporal Knowledge Graph Reasoning with Historical Contrastive Learning](https://mlsanity.com/paper/2211.10904/) (2022)
- [Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval](https://mlsanity.com/paper/1805.07591/) (2018)
- [Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Setting](https://mlsanity.com/paper/2205.04692/) (2022)
- [TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph](https://mlsanity.com/paper/2205.14307/) (2022)
- [HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces](https://mlsanity.com/paper/2312.13680/) (2023)
- [Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph](https://mlsanity.com/paper/2405.00352/) (2024)
- [GTRL: An Entity Group-Aware Temporal Knowledge Graph Representation Learning Method](https://mlsanity.com/paper/2302.11091/) (2023)
- [DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach](https://mlsanity.com/paper/2410.22631/) (2024)

## Abstract (arXiv)

Temporal Knowledge Graph Reasoning (TKGR) aims to complete missing factual elements along the timeline. Depending on the temporal position of the query, the task is categorized into interpolation and extrapolation. Existing interpolation methods typically embed temporal information into individual facts to complete missing historical knowledge, while extrapolation techniques often leverage sequence models over graph snapshots to identify recurring patterns for future event prediction. These methods face two critical challenges: limited contextual modeling in interpolation and cognitive generalization bias in extrapolation. To address these, we propose a unified method for TKGR, dubbed DynaGen. For interpolation, DynaGen dynamically constructs entity-centric subgraphs and processes them with a synergistic dual-branch GNN encoder to capture evolving structural context. For extrapolation, it applies a conditional diffusion process, which forces the model to learn underlying evolutionary principles rather than just superficial patterns, enhancing its ability to predict unseen future events. Extensive experiments on six benchmark datasets show DynaGen achieves state-of-the-art performance. On average, compared to the second-best models, DynaGen improves the Mean Reciprocal Rank (MRR) score by 2.61 points for interpolation and 1.45 points for extrapolation.