← Search

Chenglu Pan

2 accepted papers

2024

Measuring Task Similarity and Its Implication in Fine-Tuning Graph Neural Networks

AAAI 2024technical

The paradigm of pre-training and fine-tuning graph neural networks has attracted wide research attention. In previous studies, the pre-trained models are viewed as universally versatile, and applied for a diverse range of downstream tasks. In many situations, however, this practice results in limite…

2024

Towards Fair Graph Federated Learning via Incentive Mechanisms

AAAI 2024technical

Graph federated learning (FL) has emerged as a pivotal paradigm enabling multiple agents to collaboratively train a graph model while preserving local data privacy. Yet, current efforts overlook a key issue: agents are self-interested and would hesitant to share data without fair and satisfactory i…