# Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs

arXiv: https://arxiv.org/abs/2003.13432 · HTML: https://mlsanity.com/paper/2003.13432/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 10 of 10)

- [Temporal Knowledge Graph Forecasting with Neural ODE](https://mlsanity.com/paper/2101.05151/) (2021)
- [ChronoR: Rotation Based Temporal Knowledge Graph Embedding](https://mlsanity.com/paper/2103.10379/) (2021)
- [A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges](https://mlsanity.com/paper/2405.00476/) (2024)
- [Graph Neural Networks Designed for Different Graph Types: A Survey](https://mlsanity.com/paper/2204.03080/) (2022)
- [TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2104.08419/) (2021)
- [TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer](https://mlsanity.com/paper/2506.00431/) (2025)
- [Sparse-Dyn: Sparse Dynamic Graph Multi-representation Learning via Event-based Sparse Temporal Attention Network](https://mlsanity.com/paper/2201.01384/) (2022)
- [Temporal Smoothness Regularisers for Neural Link Predictors](https://mlsanity.com/paper/2309.09045/) (2023)
- [Modeling the evolution of temporal knowledge graphs with uncertainty](https://mlsanity.com/paper/2301.04977/) (2023)
- [Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix](https://mlsanity.com/paper/2605.16112/) (2026)

## Abstract (arXiv)

The Hawkes process has become a standard method for modeling self-exciting event sequences with different event types. A recent work has generalized the Hawkes process to a neurally self-modulating multivariate point process, which enables the capturing of more complex and realistic impacts of past events on future events. However, this approach is limited by the number of possible event types, making it impossible to model the dynamics of evolving graph sequences, where each possible link between two nodes can be considered as an event type. The number of event types increases even further when links are directional and labeled. To address this issue, we propose the Graph Hawkes Neural Network that can capture the dynamics of evolving graph sequences and can predict the occurrence of a fact in a future time instance. Extensive experiments on large-scale temporal multi-relational databases, such as temporal knowledge graphs, demonstrate the effectiveness of our approach.