# Data-centric Prompt Tuning for Dynamic Graphs

arXiv: https://arxiv.org/abs/2601.11954 · HTML: https://mlsanity.com/paper/2601.11954/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [GPT-GNN: Generative Pre-Training of Graph Neural Networks](https://mlsanity.com/paper/2006.15437/) (2020)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://mlsanity.com/paper/2302.08043/) (2023)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey](https://mlsanity.com/paper/2005.07496/) (2020)
- [MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation](https://mlsanity.com/paper/1908.00413/) (2019)
- [Meta-GNN: On Few-shot Node Classification in Graph Meta-learning](https://mlsanity.com/paper/1905.09718/) (2019)
- [OpenGraph: Towards Open Graph Foundation Models](https://mlsanity.com/paper/2403.01121/) (2024)
- [Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings](https://mlsanity.com/paper/1904.11547/) (2019)
- [Graph Few-shot Learning via Knowledge Transfer](https://mlsanity.com/paper/1910.03053/) (2019)
- [Graph Prompt Learning: A Comprehensive Survey and Beyond](https://mlsanity.com/paper/2311.16534/) (2023)
- [A Survey on Embedding Dynamic Graphs](https://mlsanity.com/paper/2101.01229/) (2021)
- [All-in-one: Multi-task Learning for Rumour Verification](https://mlsanity.com/paper/1806.03713/) (2018)
- [HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learning](https://mlsanity.com/paper/2312.01878/) (2023)
- [MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs](https://mlsanity.com/paper/2312.03731/) (2023)
- [Semi-decentralized Federated Ego Graph Learning for Recommendation](https://mlsanity.com/paper/2302.10900/) (2023)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Prompt Learning on Temporal Interaction Graphs](https://mlsanity.com/paper/2402.06326/) (2024)

## Built on by (most cited first, 2 of 2)

- [Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts](https://mlsanity.com/paper/2608.06031/) (2026)
- [Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models](https://mlsanity.com/paper/2605.13540/) (2026)

## Abstract (arXiv)

Dynamic graphs have attracted increasing attention due to their ability to model complex and evolving relationships in real-world scenarios. Traditional approaches typically pre-train models using dynamic link prediction and directly apply the resulting node temporal embeddings to specific downstream tasks. However, the significant differences among downstream tasks often lead to performance degradation, especially under few-shot settings. Prompt tuning has emerged as an effective solution to this problem. Existing prompting methods are often strongly coupled with specific model architectures or pretraining tasks, which makes it difficult to adapt to recent or future model designs. Moreover, their exclusive focus on modifying node or temporal features while neglecting spatial structural information leads to limited expressiveness and degraded performance. To address these limitations, we propose DDGPrompt, a data-centric prompting framework designed to effectively refine pre-trained node embeddings at the input data level, enabling better adaptability to diverse downstream tasks. We first define a unified node expression feature matrix that aggregates all relevant temporal and structural information of each node, ensuring compatibility with a wide range of dynamic graph models. Then, we introduce three prompt matrices (temporal bias, edge weight, and feature mask) to adjust the feature matrix completely, achieving task-specific adaptation of node embeddings. We evaluate DDGPrompt under a strict few-shot setting on four public dynamic graph datasets. Experimental results demonstrate that our method significantly outperforms traditional methods and prompting approaches in scenarios with limited labels and cold-start conditions.