Curriculum learning for graph neural networks: Which edges should we learn first

Z Zhang, J Wang, L Zhao - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Abstract Graph Neural Networks (GNNs) have achieved great success in representing data
with dependencies by recursively propagating and aggregating messages along the edges …

Multifidelity graph neural networks for efficient and accurate mesh‐based partial differential equations surrogate modeling

M Taghizadeh, MA Nabian… - Computer‐Aided Civil …, 2024 - Wiley Online Library
Accurately predicting the dynamics of complex systems governed by partial differential
equations (PDEs) is crucial in various applications. Traditional numerical methods such as …

Data-centric graph learning: A survey

C Yang, D Bo, J Liu, Y Peng, B Chen, H Dai… - arxiv preprint arxiv …, 2023 - arxiv.org
The history of artificial intelligence (AI) has witnessed the significant impact of high-quality
data on various deep learning models, such as ImageNet for AlexNet and ResNet. Recently …

Data-centric graph learning: A survey

Y Guo, D Bo, C Yang, Z Lu, Z Zhang… - … Transactions on Big …, 2024 - ieeexplore.ieee.org
The history of artificial intelligence (AI) has witnessed the significant impact of high-quality
data on various deep learning models, such as ImageNet for AlexNet and ResNet. Recently …

Weighted self-paced learning with belief functions

S Zhang, D Han, J Dezert, Y Yang - Expert Systems with Applications, 2024 - Elsevier
Employing a learning strategy analogous to human, from the easy to the difficult, better
classifiers could be achieved in a complicated pattern classification from different domains …

Navigating complexity: Toward lossless graph condensation via expanding window matching

Y Zhang, T Zhang, K Wang, Z Guo, Y Liang… - arxiv preprint arxiv …, 2024 - arxiv.org
Graph condensation aims to reduce the size of a large-scale graph dataset by synthesizing
a compact counterpart without sacrificing the performance of Graph Neural Networks …

Mitigating label noise on graph via topological sample selection

Y Wu, J Yao, X **a, J Yu, R Wang, B Han… - arxiv preprint arxiv …, 2024 - arxiv.org
Despite the success of the carefully-annotated benchmarks, the effectiveness of existing
graph neural networks (GNNs) can be considerably impaired in practice when the real-world …

Data-augmented curriculum graph neural architecture search under distribution shifts

Y Yao, X Wang, Y Qin, Z Zhang, W Zhu… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Graph neural architecture search (NAS) has achieved great success in designing
architectures for graph data processing. However, distribution shifts pose great challenges …

Graph principal flow network for conditional graph generation

Z Mo, T Luo, SJ Pan - Proceedings of the ACM on Web Conference 2024, 2024 - dl.acm.org
Conditional graph generation is crucial and challenging since the conditional distribution of
graph topology and feature is complicated and the semantic information is hard to capture …

Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification

B **e, H Chang, Z Zhang, Z Zhang, S Wu… - Proceedings of the 30th …, 2024 - dl.acm.org
Graph Neural Architecture Search (GNAS) has achieved superior performance on various
graph-structured tasks. However, existing GNAS studies overlook the applications of GNAS …