篇名 |
INAMA: An Interactive Attentional Model for Node Alignment
|
---|---|
並列篇名 | INAMA: An Interactive Attentional Model for Node Alignment |
作者 | Zhichao Huang、Yuxi Sun、Yunming Ye、Wensheng Gan、Wei-Che Chien |
英文摘要 | Because of wide studies of Social Network Analysis (SNA), identifying users from heterogeneous platforms, also known as node alignment, has gradually become a research hotspot. In this paper, we propose an INteractive Attentional Model for Node Alignment, namely INAMA. To tackle the issue, the model leverages both topology structures and node attributes. First, we define the matched neighbors instead of the original topology structures, which consist of neighbors from the aligned pairs. By doing so, our model can efficiently leverage topology information. Then, an interactive attentional model is built to model node message passing processes. Specifically, intra and inter attentional mechanisms are introduced to determine the neighbor influences from local and across networks, respectively. Finally, we evaluate our model on six real-world datasets and the experimental results demonstrate the effectiveness of our model. |
起訖頁 | 1587-1597 |
關鍵詞 | Node alignment、Interactive attentional model、Matched neighbors、Intra and inter |
刊名 | 網際網路技術學刊 |
期數 | 202112 (22:7期) |
出版單位 | 台灣學術網路管理委員會 |
DOI |
|
QR Code | |
該期刊 上一篇
| Using Fitness Dependent Optimizer for Training Multi-layer Perceptron |
該期刊 下一篇
| To Implement Computerized Adaptive Testing by Automatically Adjusting Item Difficulty Index on Adaptive English Learning Platform |