# Learning Across Temporal Graph Representation Silos

arXiv: https://arxiv.org/abs/2610.19576 · HTML: https://mlsanity.com/paper/2610.19576/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 14 Oct 2026.

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

- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [History repeats Itself: A Baseline for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2404.16726/) (2024)
- [UTG: Towards a Unified View of Snapshot and Event Based Models for Temporal Graphs](https://mlsanity.com/paper/2407.12269/) (2024)
- [Towards Foundation Model on Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2506.06367/) (2025)
- [Temporal Graph Pattern Machine](https://mlsanity.com/paper/2601.22454/) (2026)
- [Mining Temporal Attack Patterns from Cyberthreat Intelligence Reports](https://mlsanity.com/paper/2401.01883/) (2024)
- [Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding](https://mlsanity.com/paper/2602.13075/) (2026)
- [Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models](https://mlsanity.com/paper/2605.13540/) (2026)

## Abstract (arXiv)

Temporal graph data are recorded in different representations, but whether these differences also determine the scope of learned knowledge reuse remains unclear. This study investigates whether predictive structure learned from relational histories can be reused between continuous-time dynamic graphs (CTDGs) and temporal knowledge graphs (TKGs). Bidirectional reuse emerges while retaining distinct input and prediction interfaces and independent vocabularies, and sources with the same representation are not always more useful. Controlled reorganizations of source histories show that the organization contributing to reuse varies across source-target conditions. We show that learned aspects of Relational Dynamics, the predictive structure present in relational histories, can be reused across conventional representation boundaries. Independently pretrained TKG and CTDG learners can also be fused at the score level to improve prediction on a third dataset without entity or relation-semantic alignment. Two proofs of concept in recommendation and security detection illustrate that external temporal sources without direct alignment can also become useful pretraining resources.