3 citations · 5 across the 3 of their papers we have counts for
3 papers
Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks
Vijay Lingam, Rahul Ragesh, Arun Iyer +1
Graph Neural Networks (GNNs) exhibit excellent performance when graphs have strong homophily property, i.e. connected nodes have the same labels. However, they perform poorly on he…
User Embedding based Neighborhood Aggregation Method for Inductive Recommendation
Rahul Ragesh, Sundararajan Sellamanickam, Vijay Lingam +2
We consider the problem of learning latent features (aka embedding) for users and items in a recommendation setting. Given only a user-item interaction graph, the goal is to recomm…
A Graph Convolutional Network Composition Framework for Semi-supervised Classification
Rahul Ragesh, Sundararajan Sellamanickam, Vijay Lingam +1
Graph convolutional networks (GCNs) have gained popularity due to high performance achievable on several downstream tasks including node classification. Several architectural varia…