Fairness-aware predictive graph learning in social networks
- Wang, Lei, Yu, Shuo, Febrinanto, Falih, Alqahtani, Fayez, El-Tobely, Tarek
- Authors: Wang, Lei , Yu, Shuo , Febrinanto, Falih , Alqahtani, Fayez , El-Tobely, Tarek
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics Vol. 10, no. 15 (2022), p.
- Full Text:
- Reviewed:
- Description: Predictive graph learning approaches have been bringing significant advantages in many real-life applications, such as social networks, recommender systems, and other social-related downstream tasks. For those applications, learning models should be able to produce a great prediction result to maximize the usability of their application. However, the paradigm of current graph learning methods generally neglects the differences in link strength, leading to discriminative predictive results, resulting in different performance between tasks. Based on that problem, a fairness-aware predictive learning model is needed to balance the link strength differences and not only consider how to formulate it. To address this problem, we first formally define two biases (i.e., Preference and Favoritism) that widely exist in previous representation learning models. Then, we employ modularity maximization to distinguish strong and weak links from the quantitative perspective. Eventually, we propose a novel predictive learning framework entitled ACE that first implements the link strength differentiated learning process and then integrates it with a dual propagation process. The effectiveness and fairness of our proposed ACE have been verified on four real-world social networks. Compared to nine different state-of-the-art methods, ACE and its variants show better performance. The ACE framework can better reconstruct networks, thus also providing a high possibility of resolving misinformation in graph-structured data. © 2022 by the authors.
- Authors: Wang, Lei , Yu, Shuo , Febrinanto, Falih , Alqahtani, Fayez , El-Tobely, Tarek
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics Vol. 10, no. 15 (2022), p.
- Full Text:
- Reviewed:
- Description: Predictive graph learning approaches have been bringing significant advantages in many real-life applications, such as social networks, recommender systems, and other social-related downstream tasks. For those applications, learning models should be able to produce a great prediction result to maximize the usability of their application. However, the paradigm of current graph learning methods generally neglects the differences in link strength, leading to discriminative predictive results, resulting in different performance between tasks. Based on that problem, a fairness-aware predictive learning model is needed to balance the link strength differences and not only consider how to formulate it. To address this problem, we first formally define two biases (i.e., Preference and Favoritism) that widely exist in previous representation learning models. Then, we employ modularity maximization to distinguish strong and weak links from the quantitative perspective. Eventually, we propose a novel predictive learning framework entitled ACE that first implements the link strength differentiated learning process and then integrates it with a dual propagation process. The effectiveness and fairness of our proposed ACE have been verified on four real-world social networks. Compared to nine different state-of-the-art methods, ACE and its variants show better performance. The ACE framework can better reconstruct networks, thus also providing a high possibility of resolving misinformation in graph-structured data. © 2022 by the authors.
CenGCN : centralized convolutional networks with vertex imbalance for scale-free graphs
- Xia, Feng, Wang, Lei, Tang, Tao, Chen, Xin, Kong, Xiangjie, Oatley, Giles, King, Irwin
- Authors: Xia, Feng , Wang, Lei , Tang, Tao , Chen, Xin , Kong, Xiangjie , Oatley, Giles , King, Irwin
- Date: 2023
- Type: Text , Journal article
- Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 5 (2023), p. 4555-4569
- Full Text:
- Reviewed:
- Description: Graph Convolutional Networks (GCNs) have achieved impressive performance in a wide variety of areas, attracting considerable attention. The core step of GCNs is the information-passing framework that considers all information from neighbors to the central vertex to be equally important. Such equal importance, however, is inadequate for scale-free networks, where hub vertices propagate more dominant information due to vertex imbalance. In this paper, we propose a novel centrality-based framework named CenGCN to address the inequality of information. This framework first quantifies the similarity between hub vertices and their neighbors by label propagation with hub vertices. Based on this similarity and centrality indices, the framework transforms the graph by increasing or decreasing the weights of edges connecting hub vertices and adding self-connections to vertices. In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices. We present two variants CenGCN_D and CenGCN_E, based on degree centrality and eigenvector centrality, respectively. We also conduct comprehensive experiments, including vertex classification, link prediction, vertex clustering, and network visualization. The results demonstrate that the two variants significantly outperform state-of-the-art baselines. © 1989-2012 IEEE.
- Authors: Xia, Feng , Wang, Lei , Tang, Tao , Chen, Xin , Kong, Xiangjie , Oatley, Giles , King, Irwin
- Date: 2023
- Type: Text , Journal article
- Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 5 (2023), p. 4555-4569
- Full Text:
- Reviewed:
- Description: Graph Convolutional Networks (GCNs) have achieved impressive performance in a wide variety of areas, attracting considerable attention. The core step of GCNs is the information-passing framework that considers all information from neighbors to the central vertex to be equally important. Such equal importance, however, is inadequate for scale-free networks, where hub vertices propagate more dominant information due to vertex imbalance. In this paper, we propose a novel centrality-based framework named CenGCN to address the inequality of information. This framework first quantifies the similarity between hub vertices and their neighbors by label propagation with hub vertices. Based on this similarity and centrality indices, the framework transforms the graph by increasing or decreasing the weights of edges connecting hub vertices and adding self-connections to vertices. In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices. We present two variants CenGCN_D and CenGCN_E, based on degree centrality and eigenvector centrality, respectively. We also conduct comprehensive experiments, including vertex classification, link prediction, vertex clustering, and network visualization. The results demonstrate that the two variants significantly outperform state-of-the-art baselines. © 1989-2012 IEEE.
- «
- ‹
- 1
- ›
- »