تقرير
tBDFS: Temporal Graph Neural Network Leveraging DFS
| العنوان: | tBDFS: Temporal Graph Neural Network Leveraging DFS |
|---|---|
| المؤلفون: | Singer, Uriel, Roitman, Haggai, Guy, Ido, Radinsky, Kira |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning |
| الوصف: | Temporal graph neural networks (temporal GNNs) have been widely researched, reaching state-of-the-art results on multiple prediction tasks. A common approach employed by most previous works is to apply a layer that aggregates information from the historical neighbors of a node. Taking a different research direction, in this work, we propose tBDFS -- a novel temporal GNN architecture. tBDFS applies a layer that efficiently aggregates information from temporal paths to a given (target) node in the graph. For each given node, the aggregation is applied in two stages: (1) A single representation is learned for each temporal path ending in that node, and (2) all path representations are aggregated into a final node representation. Overall, our goal is not to add new information to a node, but rather observe the same exact information in a new perspective. This allows our model to directly observe patterns that are path-oriented rather than neighborhood-oriented. This can be thought as a Depth-First Search (DFS) traversal over the temporal graph, compared to the popular Breath-First Search (BFS) traversal that is applied in previous works. We evaluate tBDFS over multiple link prediction tasks and show its favorable performance compared to state-of-the-art baselines. To the best of our knowledge, we are the first to apply a temporal-DFS neural network. Comment: 9 pages, 2 figures, 2 tables |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2206.05692 |
| رقم الأكسشن: | edsarx.2206.05692 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |