Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2408.08508 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914913687961600 |
|---|---|
| author | He, Fang Deng, Jinhai Xue, Ruizhan Wang, Maojun Zhang, Zeyu |
| author_facet | He, Fang Deng, Jinhai Xue, Ruizhan Wang, Maojun Zhang, Zeyu |
| contents | Like Graph Neural Networks (GNNs), Signed Graph Neural Networks (SGNNs) are also up against fairness issues from source data and typical aggregation method. In this paper, we are pioneering to make the investigation of fairness in SGNNs expanded from GNNs. We identify the issue of degree bias within signed graphs, offering a new perspective on the fairness issues related to SGNNs. To handle the confronted bias issue, inspired by previous work on degree bias, a new Model-Agnostic method is consequently proposed to enhance representation of nodes with different degrees, which named as Degree Debiased Signed Graph Neural Network (DD-SGNN) . More specifically, in each layer, we make a transfer from nodes with high degree to nodes with low degree inside a head-to-tail triplet, which to supplement the underlying domain missing structure of the tail nodes and meanwhile maintain the positive and negative semantics specified by balance theory in signed graphs. We make extensive experiments on four real-world datasets. The result verifies the validity of the model, that is, our model mitigates the degree bias issue without compromising performance($\textit{i.e.}$, AUC, F1). The code is provided in supplementary material. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08508 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mitigating Degree Bias in Signed Graph Neural Networks He, Fang Deng, Jinhai Xue, Ruizhan Wang, Maojun Zhang, Zeyu Machine Learning Like Graph Neural Networks (GNNs), Signed Graph Neural Networks (SGNNs) are also up against fairness issues from source data and typical aggregation method. In this paper, we are pioneering to make the investigation of fairness in SGNNs expanded from GNNs. We identify the issue of degree bias within signed graphs, offering a new perspective on the fairness issues related to SGNNs. To handle the confronted bias issue, inspired by previous work on degree bias, a new Model-Agnostic method is consequently proposed to enhance representation of nodes with different degrees, which named as Degree Debiased Signed Graph Neural Network (DD-SGNN) . More specifically, in each layer, we make a transfer from nodes with high degree to nodes with low degree inside a head-to-tail triplet, which to supplement the underlying domain missing structure of the tail nodes and meanwhile maintain the positive and negative semantics specified by balance theory in signed graphs. We make extensive experiments on four real-world datasets. The result verifies the validity of the model, that is, our model mitigates the degree bias issue without compromising performance($\textit{i.e.}$, AUC, F1). The code is provided in supplementary material. |
| title | Mitigating Degree Bias in Signed Graph Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2408.08508 |