Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions

09/23/2019
by   Boris Knyazev, et al.
3

Graphs evolving over time are a natural way to represent data in many domains, such as social networks, bioinformatics, physics and finance. Machine learning methods for graphs, which leverage such data for various prediction tasks, have seen a recent surge of interest and capability. In practice, ground truth edges between nodes in these graphs can be unknown or suboptimal, which hurts the quality of features propagated through the network. Building on recent progress in modeling temporal graphs and learning latent graphs, we extend two methods, Dynamic Representation (DyRep) and Neural Relational Inference (NRI), for the task of dynamic link prediction. We explore the effect of learning temporal attention edges using NRI without requiring the ground truth graph. In experiments on the Social Evolution dataset, we show semantic interpretability of learned attention, often outperforming the baseline DyRep model that uses a ground truth graph to compute attention. In addition, we consider functions acting on pairs of nodes, which are used to predict link or edge representations. We demonstrate that in all cases, our bilinear transformation is superior to feature concatenation, typically employed in prior work. Source code is available at https://github.com/uoguelph-mlrg/LDG.

READ FULL TEXT

page 4

page 9

page 10

page 12

research
06/21/2021

ConvDySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention and Convolutional Neural Networks

Learning node representations on temporal graphs is a fundamental step t...
research
04/06/2023

Inductive Graph Unlearning

As a way to implement the "right to be forgotten" in machine learning, m...
research
06/30/2021

Edge Proposal Sets for Link Prediction

Graphs are a common model for complex relational data such as social net...
research
05/29/2019

Evaluating structure learning algorithms with a balanced scoring function

Several structure learning algorithms have been proposed towards discove...
research
03/01/2022

An Effective Graph Learning based Approach for Temporal Link Prediction: The First Place of WSDM Cup 2022

Temporal link prediction, as one of the most crucial work in temporal gr...
research
06/13/2023

Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs

Temporal Graph Learning, which aims to model the time-evolving nature of...
research
07/08/2022

Hidden Schema Networks

Most modern language models infer representations that, albeit powerful,...

Please sign up or login with your details

Forgot password? Click here to reset