TIGGER: Scalable Generative Modelling for Temporal Interaction Graphs
arXiv:2203.03564 · doi:10.1609/aaai.v36i6.20638
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.
arXiv commentTo be published in AAAI-2022, additionally contains technical appendices/supplementary material
References in corpus (9)
- Statistical mechanics of complex networks
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- NetGAN: Generating Graphs via Random Walks
- Efficient Graph Generation with Graph Recurrent Attention Networks
- The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
- Fully Neural Network based Model for General Temporal Point Processes
- A Tutorial on Hawkes Processes for Events in Social Media
- DYMOND: DYnamic MOtif-NoDes Network Generative Model
- Generating a Doppelganger Graph: Resembling but Distinct