Mitigating degree bias in signed graph neural networks
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 …
against fairness issues from source data and typical aggregation method. In this paper, we …
Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
Graph Neural Networks (GNNs) often perform better for high-degree nodes than low-degree
nodes on node classification tasks. This degree bias can reinforce social marginalization by …
nodes on node classification tasks. This degree bias can reinforce social marginalization by …
Topology-aware Retrieval Augmentation for Text Generation
Retrieval-augmented Generation has been used to augment Language Models by retrieving
texts from external databases. Since real-world texts are often connected in the graph (eg …
texts from external databases. Since real-world texts are often connected in the graph (eg …
Augmenting Textual Generation via Topology Aware Retrieval
Despite the impressive advancements of Large Language Models (LLMs) in generating text,
they are often limited by the knowledge contained in the input and prone to producing …
they are often limited by the knowledge contained in the input and prone to producing …
Normalize Then Propagate: Efficient Homophilous Regularization for Few-shot Semi-Supervised Node Classification
B Zhang, MC Chen, J Song, S Li, J Zhang… - arXiv preprint arXiv …, 2025 - arxiv.org
Graph Neural Networks (GNNs) have demonstrated remarkable ability in semi-supervised
node classification. However, most existing GNNs rely heavily on a large amount of labeled …
node classification. However, most existing GNNs rely heavily on a large amount of labeled …