Graph mixup with soft alignments

H Ling, Z Jiang, M Liu, S Ji… - … Conference on Machine …, 2023 - proceedings.mlr.press
We study graph data augmentation by mixup, which has been used successfully on images.
A key operation of mixup is to compute a convex combination of a pair of inputs. This …

Fused gromov-wasserstein graph mixup for graph-level classifications

X Ma, X Chu, Y Wang, Y Lin, J Zhao… - Advances in Neural …, 2024 - proceedings.neurips.cc
Graph data augmentation has shown superiority in enhancing generalizability and
robustness of GNNs in graph-level classifications. However, existing methods primarily …

Eignn: Efficient infinite-depth graph neural networks

J Liu, K Kawaguchi, B Hooi… - Advances in Neural …, 2021 - proceedings.neurips.cc
Graph neural networks (GNNs) are widely used for modelling graph-structured data in
numerous applications. However, with their inherently finite aggregation layers, existing …

Structural re-weighting improves graph domain adaptation

S Liu, T Li, Y Feng, N Tran, H Zhao… - … on Machine Learning, 2023 - proceedings.mlr.press
In many real-world applications, graph-structured data used for training and testing have
differences in distribution, such as in high energy physics (HEP) where simulation data used …

Graph transplant: Node saliency-guided graph mixup with local structure preservation

J Park, H Shim, E Yang - Proceedings of the AAAI Conference on …, 2022 - ojs.aaai.org
Graph-structured datasets usually have irregular graph sizes and connectivities, rendering
the use of recent data augmentation techniques, such as Mixup, difficult. To tackle this …

Graph neural transport networks with non-local attentions for recommender systems

H Chen, CCM Yeh, F Wang, H Yang - … of the ACM Web Conference 2022, 2022 - dl.acm.org
Graph Neural Networks (GNNs) have emerged as powerful tools for collaborative filtering. A
key challenge of recommendations is to distill long-range collaborative signals from user …

Vqamix: Conditional triplet mixup for medical visual question answering

H Gong, G Chen, M Mao, Z Li… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Medical visual question answering (VQA) aims to correctly answer a clinical question related
to a given medical image. Nevertheless, owing to the expensive manual annotations of …

Half-Hop: A graph upsampling approach for slowing down message passing

M Azabou, V Ganesh, S Thakoor… - International …, 2023 - proceedings.mlr.press
Message passing neural networks have shown a lot of success on graph-structured data.
However, there are many instances where message passing can lead to over-smoothing or …

Towards data augmentation in graph neural network: An overview and evaluation

M Adjeisah, X Zhu, H Xu, TA Ayall - Computer Science Review, 2023 - Elsevier
Abstract Many studies on Graph Data Augmentation (GDA) approaches have emerged. The
techniques have rapidly improved performance for various graph neural network (GNN) …

Graph convolution network based recommender systems: Learning guarantee and item mixture powered strategy

L Deng, D Lian, C Wu, E Chen - Advances in Neural …, 2022 - proceedings.neurips.cc
Inspired by their powerful representation ability on graph-structured data, Graph Convolution
Networks (GCNs) have been widely applied to recommender systems, and have shown …