Cargando…
Learning temporal attention in dynamic graphs with bilinear interactions
Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks. We consider a common case in which edges can be short term interactions (e.g., messaging) or long term structural connections (e.g., friendship). In practice, lon...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7932168/ https://www.ncbi.nlm.nih.gov/pubmed/33661968 http://dx.doi.org/10.1371/journal.pone.0247936 |
_version_ | 1783660426039394304 |
---|---|
author | Knyazev, Boris Augusta, Carolyn Taylor, Graham W. |
author_facet | Knyazev, Boris Augusta, Carolyn Taylor, Graham W. |
author_sort | Knyazev, Boris |
collection | PubMed |
description | Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks. We consider a common case in which edges can be short term interactions (e.g., messaging) or long term structural connections (e.g., friendship). In practice, long term edges are often specified by humans. Human-specified edges can be both expensive to produce and suboptimal for the downstream task. To alleviate these issues, we propose a model based on temporal point processes and variational autoencoders that learns to infer temporal attention between nodes by observing node communication. As temporal attention drives between-node feature propagation, using the dynamics of node interactions to learn this key component provides more flexibility while simultaneously avoiding issues associated with human-specified edges. We also propose a bilinear transformation layer for pairs of node features instead of concatenation, typically used in prior work, and demonstrate its superior performance in all cases. In experiments on two datasets in the dynamic link prediction task, our model often outperforms the baseline model that requires a human-specified graph. Moreover, our learned attention is semantically interpretable and infers connections similar to actual graphs. |
format | Online Article Text |
id | pubmed-7932168 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-79321682021-03-15 Learning temporal attention in dynamic graphs with bilinear interactions Knyazev, Boris Augusta, Carolyn Taylor, Graham W. PLoS One Research Article Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks. We consider a common case in which edges can be short term interactions (e.g., messaging) or long term structural connections (e.g., friendship). In practice, long term edges are often specified by humans. Human-specified edges can be both expensive to produce and suboptimal for the downstream task. To alleviate these issues, we propose a model based on temporal point processes and variational autoencoders that learns to infer temporal attention between nodes by observing node communication. As temporal attention drives between-node feature propagation, using the dynamics of node interactions to learn this key component provides more flexibility while simultaneously avoiding issues associated with human-specified edges. We also propose a bilinear transformation layer for pairs of node features instead of concatenation, typically used in prior work, and demonstrate its superior performance in all cases. In experiments on two datasets in the dynamic link prediction task, our model often outperforms the baseline model that requires a human-specified graph. Moreover, our learned attention is semantically interpretable and infers connections similar to actual graphs. Public Library of Science 2021-03-04 /pmc/articles/PMC7932168/ /pubmed/33661968 http://dx.doi.org/10.1371/journal.pone.0247936 Text en © 2021 Knyazev et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Knyazev, Boris Augusta, Carolyn Taylor, Graham W. Learning temporal attention in dynamic graphs with bilinear interactions |
title | Learning temporal attention in dynamic graphs with bilinear interactions |
title_full | Learning temporal attention in dynamic graphs with bilinear interactions |
title_fullStr | Learning temporal attention in dynamic graphs with bilinear interactions |
title_full_unstemmed | Learning temporal attention in dynamic graphs with bilinear interactions |
title_short | Learning temporal attention in dynamic graphs with bilinear interactions |
title_sort | learning temporal attention in dynamic graphs with bilinear interactions |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7932168/ https://www.ncbi.nlm.nih.gov/pubmed/33661968 http://dx.doi.org/10.1371/journal.pone.0247936 |
work_keys_str_mv | AT knyazevboris learningtemporalattentionindynamicgraphswithbilinearinteractions AT augustacarolyn learningtemporalattentionindynamicgraphswithbilinearinteractions AT taylorgrahamw learningtemporalattentionindynamicgraphswithbilinearinteractions |