This repository contains a list of works happened on the Temporal Dynamic Graphs, we categorize them based on ideas.

We will try to make this list updated. If you found any error or any missed paper, please don't hesitate to open issues or pull requests.

AAAI Work:

https://github.com/tonygracious/RRHyperTPP_AAAI2025

https://github.com/tonygracious/DynHyperNodeTPP_AAAI2025

Foundational models for graph link prediction problems

key questions

1. Can we build a foundational model using temporal point processes for graphs?
2. if a model trained on specific types of higher-order relations can generalize to different types in a zero-shot setting:
3. For example, can a model trained on hyperedge and bipartite link prediction effectively handle bipartite hyperedge link prediction at test timE
4. how we can tokenize graphs or nodes in a way that adapts to unseen nodes.
5. we can develop in-context learning in this case

Current State of the Models for Temporal Graph Neural Networks:

Tasks:

1. DyRep: Learning Representations over Dynamic Graphs (https://openreview.net/forum?id=HyePrhR5KX)
2. Temporal Graph Networks for Deep Learning on Dynamic Graphs (https://arxiv.org/pdf/2006.10637)

Next-token prediction for temporal graph link prediction

Graphs Pretraining and Zero-Shot Learning.

Pretraining

Zero-Shot Leaarning

foundational models for static graphs

Foundationsl models for Temporal graphs

Foundationsl models temporal point processes