TIGGER: Scalable Generative Modelling for Temporal Interaction Graphs

TL;DR

TIGGER is a scalable generative model for temporal interaction graphs that combines temporal point processes with auto-regressive modeling, enabling high-fidelity graph generation and efficient training on large datasets.

Contribution

The paper introduces TIGGER, a novel scalable generative model for temporal graphs that supports both transductive and inductive learning, overcoming limitations of existing models.

Findings

TIGGER outperforms state-of-the-art models in graph fidelity.

TIGGER is up to 1000 times faster than existing methods.

TIGGER supports scalable and flexible temporal graph generation.

Abstract

There has been a recent surge in learning generative models for graphs. While impressive progress has been made on static graphs, work on generative modeling of temporal graphs is at a nascent stage with significant scope for improvement. First, existing generative models do not scale with either the time horizon or the number of nodes. Second, existing techniques are transductive in nature and thus do not facilitate knowledge transfer. Finally, due to relying on one-to-one node mapping from source to the generated graph, existing models leak node identity information and do not allow up-scaling/down-scaling the source graph size. In this paper, we bridge these gaps with a novel generative model called TIGGER. TIGGER derives its power through a combination of temporal point processes with auto-regressive modeling enabling both transductive and inductive variants. Through extensive experiments on real datasets, we establish TIGGER generates graphs of superior fidelity, while also being up to 3 orders of magnitude faster than the state-of-the-art.