Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs
This work addresses a domain-specific problem for researchers and practitioners in temporal knowledge graph forecasting, representing an incremental improvement over prior neural Hawkes process methods.
The paper tackles the problem of modeling evolving graph sequences, such as temporal knowledge graphs, where existing methods are limited by the number of event types. It proposes the Graph Hawkes Neural Network, which effectively predicts future facts, as demonstrated by extensive experiments on large-scale datasets.
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.