.png){kind=icon}
返回
Structural and positional ensembled encoding for Graph Transformer
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2024.05.006.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In the Transformer architecture, positional encoding is a vital component because it provides the model with information about the structure and position of data. In Graph Transformer, there have been attempts to introduce different positional encodings and inject additional structural information. Therefore, in terms of integrating positional and structural information, we propose a Structural and Positional Ensembled Graph Transformer (SPEGT). We developed SPEGT by noting the different properties of structural and positional encodings of graphs and the similarity of their computational processes. We have set a unified component that integrates the functionalities: (i) Random Walk Positional Encoding, (ii) Shortest Path Distance between each node, and (iii) Hierarchical Cluster Encoding. We find a problem with a well-known positional encoding and experimentally verify that combining it with other encodings can solve their problem. In addition, SPEGT outperforms previous models on a variety of graph datasets. We also show that SPEGT using unified positional encoding, performs well on structurally indistinguishable graph data through error case analysis.
Keyword:
Graph neural network
Graph Transformer
Positional encoding
Graph clustering
Attention
期刊
IF:
3.3
论文数:
7.9K
被引数:
1.6W
机构
引用论文
Development of a novel Maillard reaction-based time–temperature indicator for monitoring the fluorescent AGE content in reheated foods.png)
RSC Advances
OAAI
RSC AdvancesIF0
OAAI分享收藏Clay mineralogical and geochemical expressions of the “Late Campanian Event” in the Aquitaine and Paris basins (France): Palaeoenvironmental implications“晚坎帕阶事件”在阿基坦盆地和巴黎盆地（法国）的粘土矿物学和地球化学表现：古环境意义
PREAI
分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏
分享收藏 没有更多内容
没有更多内容