# CID-TKG: Collaborative Historical Invariance and Evolutionary Dynamics Learning for Temporal Knowledge Graph Reasoning

arXiv: https://arxiv.org/abs/2604.09600 · HTML: https://mlsanity.com/paper/2604.09600/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 36 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Tensor Decompositions for temporal knowledge base completion](https://mlsanity.com/paper/2004.04926/) (2020)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [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)
- [Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2405.14170/) (2024)
- [Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning](https://mlsanity.com/paper/2305.10613/) (2023)
- [Temporal Knowledge Graph Completion using Box Embeddings](https://mlsanity.com/paper/2109.08970/) (2021)
- [Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2402.14382/) (2024)
- [Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph](https://mlsanity.com/paper/2405.00352/) (2024)

## Abstract (arXiv)

Temporal knowledge graph (TKG) reasoning aims to infer future facts at unseen timestamps from temporally evolving entities and relations. Despite recent progress, existing approaches still suffer from inherent limitations due to their inductive biases, as they predominantly rely on time-invariant or weakly time-dependent structures and overlook the evolutionary dynamics. To overcome this limitation, we propose a novel collaborative learning framework for TKGR (dubbed CID-TKG) that integrates evolutionary dynamics and historical invariance semantics as an effective inductive bias for reasoning. Specifically, CID-TKG constructs a historical invariance graph to capture long-term structural regularities and an evolutionary dynamics graph to model short-term temporal transitions. Dedicated encoders are then employed to learn representations from each structure. To alleviate semantic discrepancies across the two structures, we decompose relations into view-specific representations and align view-specific query representations via a contrastive objective, which promotes cross-view consistency while suppressing view-specific noise. Extensive experiments verify that our CID-TKG achieves state-of-the-art performance under extrapolation settings.