Search Results for author:
Found 5 papers, 1 papers with code
Prioritized Propagation in Graph Neural Networks
Specifically, the framework consists of three components: a backbone GNN model, a propagation controller to determine the optimal propagation steps for nodes, and a weight controller to compute the priority scores for nodes.
DropMix: Better Graph Contrastive Learning with Harder Negative Samples
Recently, Mixup has been introduced to synthesize hard negative samples in graph contrastive learning (GCL).
Graph Self-Contrast Representation Learning
Further, Since the triplet loss only optimizes the relative distance between the anchor and its positive/negative samples, it is difficult to ensure the absolute distance between the anchor and positive sample.
MUSE: Multi-View Contrastive Learning for Heterophilic Graphs
Finally, an alternating training scheme is adopted to ensure that unsupervised node representation learning and information fusion controller can mutually reinforce each other.
A Novel Noise Injection-based Training Scheme for Better Model Robustness
Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks in previous work.
