ConTIG: Continuous Representation Learning on Temporal Interaction Graphs
arXiv:2110.06088
Abstract
Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG discretely update node embeddings merely when an interaction occurs. They fail to capture the continuous dynamic evolution of embedding trajectories of nodes. In this paper, we propose a two-module framework named ConTIG, a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories. With two essential modules, our model exploit three-fold factors in dynamic networks which include latest interaction, neighbor features and inherent characteristics. In the first update module, we employ a continuous inference block to learn the nodes' state trajectories by learning from time-adjacent interaction patterns between node pairs using ordinary differential equations. In the second transform module, we introduce a self-attention mechanism to predict future node embeddings by aggregating historical temporal interaction information. Experiments results demonstrate the superiority of ConTIG on temporal link prediction, temporal node recommendation and dynamic node classification tasks compared with a range of state-of-the-art baselines, especially for long-interval interactions prediction.
arXiv comment12 pages; 6 figures
References in corpus (16)
- Inductive Representation Learning on Large Graphs
- Variational Graph Auto-Encoders
- Learning Graph Embedding with Adversarial Training Methods
- Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
- DynGEM: Deep Embedding Method for Dynamic Graphs
- Node Embedding over Temporal Graphs
- Temporal Graph Networks for Deep Learning on Dynamic Graphs
- K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
- Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
- Self-attention with Functional Time Representation Learning
- Inductive Representation Learning on Temporal Graphs
- TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
- Temporal Knowledge Graph Forecasting with Neural ODE
- Dynamic Network Embedding Survey
- GRADE: Graph Dynamic Embedding
- Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism