2 citations · 5 across the 9 of their papers we have counts for
7 papers · 1 filter
Unified Graph Prompt Learning via Low-Rank Graph Message Prompting
Beibei Wang, Bo Jiang, Ziyan Zhang +1
Graph Data Prompt (GDP), which introduces specific prompts in graph data for efficiently adapting pre-trained GNNs, has become a mainstream approach to graph fine-tuning learning p…
When Prompting Meets Spiking: Graph Sparse Prompting via Spiking Graph Prompt Learning
Bo Jiang, Weijun Zhao, Beibei Wang +1
Graph Prompt Feature (GPF) learning has been widely used in adapting pre-trained GNN model on the downstream task. GPFs first introduce some prompt atoms and then learns the optima…
Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning
Bo Jiang, Weijun Zhao, Beibei Wang +2
Recently, fine-tuning large-scale pre-trained GNNs has yielded remarkable attention in adapting pre-trained GNN models for downstream graph learning tasks. One representative fine-…
Reliable and Compact Graph Fine-tuning via GraphSparse Prompting
Bo Jiang, Hao Wu, Beibei Wang +2
Recently, graph prompt learning has garnered increasing attention in adapting pre-trained GNN models for downstream graph learning tasks. However, existing works generally conduct…
Graph Edge Representation via Tensor Product Graph Convolutional Representation
Bo Jiang, Sheng Ge, Ziyan Zhang +3
Graph Convolutional Networks (GCNs) have been widely studied. The core of GCNs is the definition of convolution operators on graphs. However, existing Graph Convolution (GC) operat…
A Unified Graph Selective Prompt Learning for Graph Neural Networks
Bo Jiang, Hao Wu, Ziyan Zhang +2
In recent years, graph prompt learning/tuning has garnered increasing attention in adapting pre-trained models for graph representation learning. As a kind of universal graph promp…
Generalizing Aggregation Functions in GNNs:High-Capacity GNNs via Nonlinear Neighborhood Aggregators
Beibei Wang, Bo Jiang
Graph neural networks (GNNs) have achieved great success in many graph learning tasks. The main aspect powering existing GNNs is the multi-layer network architecture to learn the n…