Forecasting interaction order on temporal graphs
Link prediction is a fundamental task for graph analysis and the topic has been studied extensively for static or dynamic graphs. Essentially, the link prediction is formulated as a binary classification problem about two nodes. However, for temporal graphs, links (or interactions) among node sets a...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6134 https://ink.library.smu.edu.sg/context/sis_research/article/7137/viewcontent/3447548.3467341.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Summary: | Link prediction is a fundamental task for graph analysis and the topic has been studied extensively for static or dynamic graphs. Essentially, the link prediction is formulated as a binary classification problem about two nodes. However, for temporal graphs, links (or interactions) among node sets appear in sequential orders. And the orders may lead to interesting applications. While a binary link prediction formulation fails to handle such an order-sensitive case. In this paper, we focus on such an interaction order prediction (IOP) problem among a given node set on temporal graphs. For the technical aspect, we develop a graph neural network model named Temporal ATtention network (TAT), which utilizes the finegrained time information on temporal graphs by encoding continuous real-valued timestamps as vectors. For each transformation layer of the model, we devise an attention mechanism to aggregate neighborhoods’ information based on their representations and time encodings attached to their specific edges. We also propose a novel training scheme to address the permutation-sensitive property of the IOP problem. Experiments on several real-world temporal graphs reveal that TAT outperforms some state-of-the-art graph neural networks by 55% on average under the AUC metric. |
---|