Search Results for author:
Found 8 papers, 1 papers with code
Hyperedge Interaction-aware Hypergraph Neural Network
In this paper, we propose HeIHNN, a hyperedge interaction-aware hypergraph neural network, which captures the interactions among hyperedges during the convolution process and introduce a novel mechanism to enhance information flow between hyperedges and nodes.
Semi-supervised learning via DQN for log anomaly detection
DQNLog leverages a small amount of labeled data and a large-scale unlabeled dataset, effectively addressing the challenges of imbalanced data and limited labeling.
HC-Ref: Hierarchical Constrained Refinement for Robust Adversarial Training of GNNs
Recent studies have shown that attackers can catastrophically reduce the performance of GNNs by maliciously modifying the graph structure or node features on the graph.
Unrestricted Adversarial Samples Based on Non-semantic Feature Clusters Substitution
Most current methods generate adversarial examples with the $L_p$ norm specification.
Fine-grained Graph Learning for Multi-view Subspace Clustering
To utilize the multi-view information sufficiently, we design a specific graph learning method by introducing graph regularization and a local structure fusion pattern.
Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense
In this paper, we develop deeper insights into the Mettack algorithm, which is a representative grey-box attacking method, and then we propose a gradient-based black-box attacking algorithm.
I-GCN: Robust Graph Convolutional Network via Influence Mechanism
While being able to achieve desirable performance when the perturbation rates are low, such methods are still vulnerable to high perturbation rates.
Automatic Lumbar Spinal CT Image Segmentation with a Dual Densely Connected U-Net
The clinical treatment of degenerative and developmental lumbar spinal stenosis (LSS) is different.
