TIG-IM: A Two-Stage Inductive GNN With Multi-Task Learning for Influential Node Identification in Complex Networks
IEEE Transactions on Knowledge and Data Engineering · 2026-07 · 38 (7) · 4776-4790
DOI: 10.1109/tkde.2026.3681944 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-07. Verfasst von Yonggang Li und 3 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Joint Fund Project of China Unicom Software Research Institute and UESTC, Major Project of Science and Technology Research Program of Chongqing Municipal Education Commission, General Project of Chongqing Natural Science Foundation.
Abstract (Originalsprache)
Identifying influential nodes in complex networks poses a significant challenge, requiring a delicate balance among efficiency, accuracy, and redundancy elimination. To address this, we propose TIG-IM (A Two-stage Inductive GNN for Influence Maximization), a novel framework based on GNN. In Stage 1, we construct a multi-task learning-based global scorer. This scorer utilizes a Graph Attention Network (GAT) to simultaneously regress the SIR propagation score and our newly proposed 3D-Bridging Centrality. This multi-task design enables efficient identification of cross-community bridge nodes to generate a high-quality candidate pool. In Stage 2, we design a local selector that introduces a composite loss function with sparsity and diversity regularization. This selector performs a secondary re-ranking on the candidate subgraph to produce a final seed set that is both structurally dispersed and possesses complementary propagation potential. Theoretical analysis proves that our scorer satisfies monotonicity and that the local loss can be interpreted as a MAP estimation. Extensive experiments on twelve real-world networks from diverse domains, including social, academic, and biological, demonstrate that TIG-IM significantly outperforms various state-of-the-art baselines in both spreading effectiveness and computational efficiency. Ablation studies further validate the synergistic value of our three core components: 3D-Bridging Centrality, sparsity penalty, and diversity-based re-ranking.
Förderung
- Joint Fund Project of China Unicom Software Research Institute and UESTC
- Major Project of Science and Technology Research Program of Chongqing Municipal Education Commission
- General Project of Chongqing Natural Science Foundation
Zitieren
APA
Li, Y., Xiao, Z., Zhang, Y., & Li, L. (2026). TIG-IM: A Two-Stage Inductive GNN With Multi-Task Learning for Influential Node Identification in Complex Networks. IEEE Transactions on Knowledge and Data Engineering, 38(7), 4776-4790. https://doi.org/10.1109/tkde.2026.3681944
Vancouver
Li Y, Xiao Z, Zhang Y, Li L. TIG-IM: A Two-Stage Inductive GNN With Multi-Task Learning for Influential Node Identification in Complex Networks. IEEE Transactions on Knowledge and Data Engineering. 2026;38(7):4776-4790. doi:10.1109/tkde.2026.3681944
BibTeX
@article{Li2026,
author = {Li, Yonggang and Xiao, Zhili and Zhang, Yuanjin and Li, Longjiang},
title = {TIG-IM: A Two-Stage Inductive GNN With Multi-Task Learning for Influential Node Identification in Complex Networks},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2026},
volume = {38},
number = {7},
pages = {4776--4790},
doi = {10.1109/tkde.2026.3681944}
}
EUVIMED