TY - GEN
T1 - Does Degree Capture It All? A Case Study of Centrality and Clustering in Signed Networks
AU - Murali, Sidhaarth S.
AU - Abhin, B.
AU - Shetty, Ramya D.
AU - Bhattacharjee, Shrutilipi
N1 - Publisher Copyright:
© 2024 Copyright held by the owner/author(s).
PY - 2025/6/25
Y1 - 2025/6/25
N2 - Signed graph networks are used to model systems that contain both positive and negative components. By incorporating signed information into Graph Neural Networks (GNNs), allow for the analysis of complex interactions between nodes, facilitating tasks such as sentiment analysis and trust prediction in social networks. Our main goal in this study is to improve feature selection in a benchmark GNN, Signed Graph Attention (SiGAT) by including centrality and clustering measures other than degree. Our studies reveal that using both degree and centrality features slightly improves signed link prediction performance. Further, our ablation studies revealed that 6 degree features and 16 attention heads optimally encode information and reduce noise.
AB - Signed graph networks are used to model systems that contain both positive and negative components. By incorporating signed information into Graph Neural Networks (GNNs), allow for the analysis of complex interactions between nodes, facilitating tasks such as sentiment analysis and trust prediction in social networks. Our main goal in this study is to improve feature selection in a benchmark GNN, Signed Graph Attention (SiGAT) by including centrality and clustering measures other than degree. Our studies reveal that using both degree and centrality features slightly improves signed link prediction performance. Further, our ablation studies revealed that 6 degree features and 16 attention heads optimally encode information and reduce noise.
UR - https://www.scopus.com/pages/publications/105012254475
UR - https://www.scopus.com/pages/publications/105012254475#tab=citedBy
U2 - 10.1145/3703323.3703702
DO - 10.1145/3703323.3703702
M3 - Conference contribution
AN - SCOPUS:105012254475
T3 - CODS-COMAD 2024 - Proceedings of the 8th Jpint International Conference on Data Science and Management of Data
SP - 320
EP - 322
BT - CODS-COMAD 2024 - Proceedings of the 8th Jpint International Conference on Data Science and Management of Data
PB - Association for Computing Machinery, Inc
T2 - 8th Joint International Conference on Data Science and Management of Data, CODS-COMAD 2024
Y2 - 18 December 2024 through 21 December 2024
ER -