4 papers
Closed-Form Node Classification with Exact Graph Unlearning
Aditya Gaur, Charu Sharma
Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that, when properly tuned, class…
Federated Spectral Graph Transformers Meet Neural Ordinary Differential Equations for Non-IID Graphs
Kishan Gurumurthy, Himanshu Pal, Charu Sharma
Graph Neural Network (GNN) research is rapidly advancing due to GNNs' capacity to learn distributed representations from graph-structured data. However, centralizing large volumes…
Predict Confidently, Predict Right: Abstention in Dynamic Graph Learning
Jayadratha Gayen, Himanshu Pal, Naresh Manwani +1
Many real-world systems can be modeled as dynamic graphs, where nodes and edges evolve over time, requiring specialized models to capture their evolving dynamics in risk-sensitive…
Node Classification With Integrated Reject Option
Uday Bhaskar, Jayadratha Gayen, Charu Sharma +1
One of the key tasks in graph learning is node classification. While Graph neural networks have been used for various applications, their adaptivity to reject option setting is not…