Search Results for author:
Found 9 papers, 1 papers with code
A Piece-wise Polynomial Filtering Approach for Graph Neural Networks
We study various aspects of our proposed model including, dependency on the number of eigencomponents utilized, latent polynomial filters learned, and performance of the individual polynomials on the node classification task.
Effective Polynomial Filter Adaptation for Graph Neural Networks
We study various aspects of our proposed model including, dependency on the number of eigencomponents utilized, latent polynomial filters learned, and performance of the individual polynomials on the node classification task.
Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks
More recent approaches adapt the eigenvalues of the graph.
Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
Our approach achieves up to ~30% improvement in performance over state-of-the-art methods on heterophilic graphs.
Ranked #2 on
Node Classification
on Crocodile
GLAM: Graph Learning by Modeling Affinity to Labeled Nodes for Graph Neural Networks
Graph Neural Networks have shown excellent performance on semi-supervised classification tasks.
User Embedding based Neighborhood Aggregation Method for Inductive Recommendation
CF-LGCN-U models naturally possess the inductive capability for new items, and we propose a simple solution to generalize for new users.
S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
We propose a framework for semi-supervised training of cGANs which utilizes sparse labels to learn the conditional mapping, and at the same time leverages a large amount of unsupervised data to learn the unconditional distribution.
HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification
We consider the problem of learning efficient and inductive graph convolutional networks for text classification with a large number of examples and features.
A Graph Convolutional Network Composition Framework for Semi-supervised Classification
Graph convolutional networks (GCNs) have gained popularity due to high performance achievable on several downstream tasks including node classification.
