arXiv:2505. 16903v2 Announce Type: replace Abstract: Prompt tuning has become a key mechanism for adapting pre-trained Graph Neural Networks (GNNs) to new downstream tasks.
By Peyman Baghershahi, Sourav Medya
arXiv:2607. 14705v1 Announce Type: new Abstract: Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race.
By Yuchang Zhu, Zezhong Xie, Huizhe Zhang, Huazhen Zhong, Jintang Li, Liang Chen, Zibin Zheng
arXiv:2608. 04381v1 Announce Type: cross Abstract: Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attributes in the input space.
By Tinghe Zhang, Jian Xu, Jiaheng Chen, Jiaxing Li, Yucheng Xiao, Qiang Wang
The paper introduces TPGC, a dual-prior prompt initialization method for multi-task graph pre-training. It first uses a Task-Prior Injection Module to pre-train prompts on an auxiliary graph, then a Structure-Prior Injection Module to embed global structural context into layer-wise prompt vectors. Experiments on six node and graph classification benchmarks show that TPGC outperforms state‑of‑the‑art baselines in few‑shot settings while requiring fewer tunable parameters and less runtime.
By Zhiyang Qiu, Yangtao Wang, Xiaocui Li, Yanzhao Xie, Siyuan Chen, Wensheng Zhang
Subgraph Filtering for Fair Graph Neural Networks (SF‑GNN) is a lightweight, architecture‑agnostic framework that reduces structural bias in GNNs by identifying and filtering bias‑prone edges during message passing. It combines sensitive homophily with structural propagation amplifiers such as hub participation and triadic closure to detect problematic edges, then applies stochastic edge filtering to downweight or remove them while preserving the rest of the graph. Experiments on five benchmark datasets demonstrate that SF‑GNN consistently improves fairness while maintaining competitive predictive performance, achieving a better fairness–accuracy trade‑off than recent fairness‑aware GNN baselines.
By Haohui Lu, jiyuan Tian, Fangyu Zhou, Shahadat Uddin
MUGEN is a framework that generates unlearnable graph examples capable of protecting multiple downstream tasks—node classification, graph classification, and link prediction—simultaneously. It achieves this by perturbing a single clean dataset with a shared GNN encoder and task‑specific heads, guided by a Task‑Aligned Separability Objective (TASO) and a Type‑Adaptive Perturbation (TAP) that handles both discrete and continuous node attributes. Experiments on five benchmarks, four GNN backbones, and three learning paradigms show that MUGEN’s perturbations transfer across models and remain effective even under adversarial training and data augmentation.
By Ziyan Liu, Chengshuai Zhao, Huan Liu