作者位次 #2/6SIGIR 2026Poster· Information Retrieval (Short)
Prototype-Calibrated Graph Prompting for Few-Shot Graph Adaptation
Yumeng Zhao · Yan Yan · Chuang Zhao · Yingzi Shi · Bei Hua · Shuo Wen
摘要
Graph Neural Networks (GNNs) increasingly follow the ''pre-training, adaptation'' paradigm, where a GNN is pre-trained on large-scale graphs and then adapted to downstream tasks. Graph prompting adapts to the frozen encoder by modifying the input graph structure, rather than fine-tuning the model...