Inductive Representation Learning on Temporal Graphs

by   Da Xu, et al.

Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving topological structures. Moreover, node and topological features can be temporal as well, whose patterns the node embeddings should also capture. We propose the temporal graph attention (TGAT) layer to efficiently aggregate temporal-topological neighborhood features as well as to learn the time-feature interactions. For TGAT, we use the self-attention mechanism as building block and develop a novel functional time encoding technique based on the classical Bochner's theorem from harmonic analysis. By stacking TGAT layers, the network recognizes the node embeddings as functions of time and is able to inductively infer embeddings for both new and observed nodes as the graph evolves. The proposed approach handles both node classification and link prediction task, and can be naturally extended to include the temporal edge features. We evaluate our method with transductive and inductive tasks under temporal settings with two benchmark and one industrial dataset. Our TGAT model compares favorably to state-of-the-art baselines as well as the previous temporal graph embedding approaches.


page 1

page 2

page 3

page 4


Dynamic Graph Representation Learning via Self-Attention Networks

Learning latent representations of nodes in graphs is an important and u...

Temporal Graph Network Embedding with Causal Anonymous Walks Representations

Many tasks in graph machine learning, such as link prediction and node c...

GTEA: Representation Learning for Temporal Interaction Graphs via Edge Aggregation

We consider the problem of representation learning for temporal interact...

Representation Learning over Dynamic Graphs

How can we effectively encode evolving information over dynamic graphs i...

DynamicGEM: A Library for Dynamic Graph Embedding Methods

DynamicGEM is an open-source Python library for learning node representa...

TempNodeEmb:Temporal Node Embedding considering temporal edge influence matrix

Understanding the evolutionary patterns of real-world evolving complex s...

Neighborhood-aware Scalable Temporal Network Representation Learning

Temporal networks have been widely used to model real-world complex syst...

Please sign up or login with your details

Forgot password? Click here to reset