Search Results for author:
Found 11 papers, 7 papers with code
Your Graph Recommender is Provably a Single-view Graph Contrastive Learning
In this paper, we aim to bridge the gap between the field of GR and GCL from the perspective of encoders and loss functions.
Understanding Community Bias Amplification in Graph Representation Learning
In this work, we discover a phenomenon of community bias amplification in graph representation learning, which refers to the exacerbation of performance bias between different classes by graph representation learning.
StructComp: Substituting Propagation with Structural Compression in Training Graph Contrastive Learning
This allows the encoder not to perform any message passing during the training stage, and significantly reduces the number of sample pairs in the contrastive loss.
Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
This work provides a novel theoretical perspective for addressing the problem of imbalanced node classification in GNNs.
UNREAL:Unlabeled Nodes Retrieval and Labeling for Heavily-imbalanced Node Classification
To select which unlabeled nodes to add, we propose geometric ranking to rank unlabeled nodes.
BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
Regarding missing link inference of diverse networks, we revisit the link prediction techniques and identify the importance of both the structural and attribute information.
Stabilized Self-training with Negative Sampling on Few-labeled Graph Data
Therefore, we propose an effective framework, Stabilized self-training with Negative sampling (SN), which is applicable to existing GNNs to stabilize the training process and enhance the training data, and consequently, boost classification accuracy on graphs with few labeled data.
Scaling Up Graph Neural Networks Via Graph Coarsening
Scalability of graph neural networks remains one of the major challenges in graph machine learning.
SCE: Scalable Network Embedding from Sparsest Cut
A key of success to such contrastive learning methods is how to draw positive and negative samples.
Effective Stabilized Self-Training on Few-Labeled Graph Data
However, under extreme cases when very few labels are available (e. g., 1 labeled node per class), GNNs suffer from severe performance degradation.
Few-shot Classification on Graphs with Structural Regularized GCNs
We consider the fundamental problem of semi-supervised node classification in attributed graphs with a focus on \emph{few-shot} learning.
