DynamicG2B: Dynamic Node Classification with Layered Graph Neural Networks and BiLSTM
Most studies in graph theory assume that graphs are static, but in reality, graph structures and features change over time, leading to the concept of dynamic graphs, which is an under-researched area. Contemporary research in dynamic graph representation learning typically treats different snapshots...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
LibraryPress@UF
2023-05-01
|
| Series: | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| Online Access: | https://journals.flvc.org/FLAIRS/article/view/133309 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850271026582126592 |
|---|---|
| author | Fattah Muhammad Tahabi Xiao Luo |
| author_facet | Fattah Muhammad Tahabi Xiao Luo |
| author_sort | Fattah Muhammad Tahabi |
| collection | DOAJ |
| description | Most studies in graph theory assume that graphs are static, but in reality, graph structures and features change over time, leading to the concept of dynamic graphs, which is an under-researched area. Contemporary research in dynamic graph representation learning typically treats different snapshots of the graph as separate entities, disregarding the benefits of incorporating temporal information. While some techniques try to solve this problem using recurrent neural network-based solutions, these approaches still face the challenge of the vanishing or exploding gradient problem and complicated training procedures. To address these issues, we propose DynamicG2B, a BiLSTM-based graph neural architecture that computes node representations guided by attention using neighborhood aggregation. Our method applies relevant attention weights at different time steps to classify nodes in a supervised manner, utilizing dynamic edges and node feature information. Our evaluation of two benchmark datasets shows that DynamicG2B outperforms seven state-of-the-art baseline models in node classification in dynamic graphs. Additionally, our analysis of attention weights opens up opportunities for further research into exploring the importance of relationships among graph nodes. |
| format | Article |
| id | doaj-art-3d7e1edea2a8472bb5c46cff47314776 |
| institution | OA Journals |
| issn | 2334-0754 2334-0762 |
| language | English |
| publishDate | 2023-05-01 |
| publisher | LibraryPress@UF |
| record_format | Article |
| series | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| spelling | doaj-art-3d7e1edea2a8472bb5c46cff473147762025-08-20T01:52:22ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622023-05-013610.32473/flairs.36.13330969615DynamicG2B: Dynamic Node Classification with Layered Graph Neural Networks and BiLSTMFattah Muhammad Tahabi0https://orcid.org/0000-0002-8498-278XXiao Luo1https://orcid.org/0000-0002-3649-9785Indiana University Purdue University IndianapolisIndiana University-Purdue University IndianapolisMost studies in graph theory assume that graphs are static, but in reality, graph structures and features change over time, leading to the concept of dynamic graphs, which is an under-researched area. Contemporary research in dynamic graph representation learning typically treats different snapshots of the graph as separate entities, disregarding the benefits of incorporating temporal information. While some techniques try to solve this problem using recurrent neural network-based solutions, these approaches still face the challenge of the vanishing or exploding gradient problem and complicated training procedures. To address these issues, we propose DynamicG2B, a BiLSTM-based graph neural architecture that computes node representations guided by attention using neighborhood aggregation. Our method applies relevant attention weights at different time steps to classify nodes in a supervised manner, utilizing dynamic edges and node feature information. Our evaluation of two benchmark datasets shows that DynamicG2B outperforms seven state-of-the-art baseline models in node classification in dynamic graphs. Additionally, our analysis of attention weights opens up opportunities for further research into exploring the importance of relationships among graph nodes.https://journals.flvc.org/FLAIRS/article/view/133309 |
| spellingShingle | Fattah Muhammad Tahabi Xiao Luo DynamicG2B: Dynamic Node Classification with Layered Graph Neural Networks and BiLSTM Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| title | DynamicG2B: Dynamic Node Classification with Layered Graph Neural Networks and BiLSTM |
| title_full | DynamicG2B: Dynamic Node Classification with Layered Graph Neural Networks and BiLSTM |
| title_fullStr | DynamicG2B: Dynamic Node Classification with Layered Graph Neural Networks and BiLSTM |
| title_full_unstemmed | DynamicG2B: Dynamic Node Classification with Layered Graph Neural Networks and BiLSTM |
| title_short | DynamicG2B: Dynamic Node Classification with Layered Graph Neural Networks and BiLSTM |
| title_sort | dynamicg2b dynamic node classification with layered graph neural networks and bilstm |
| url | https://journals.flvc.org/FLAIRS/article/view/133309 |
| work_keys_str_mv | AT fattahmuhammadtahabi dynamicg2bdynamicnodeclassificationwithlayeredgraphneuralnetworksandbilstm AT xiaoluo dynamicg2bdynamicnodeclassificationwithlayeredgraphneuralnetworksandbilstm |