Curriculum learning for graph neural networks: Which edges should we learn first
Abstract Graph Neural Networks (GNNs) have achieved great success in representing data
with dependencies by recursively propagating and aggregating messages along the edges …
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
Accurately predicting the dynamics of complex systems governed by partial differential
equations (PDEs) is crucial in various applications. Traditional numerical methods such as …
equations (PDEs) is crucial in various applications. Traditional numerical methods such as …
Data-centric graph learning: A survey
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 on various deep learning models, such as ImageNet for AlexNet and ResNet. Recently …
Data-centric graph learning: A survey
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 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 …
classifiers could be achieved in a complicated pattern classification from different domains …
Navigating complexity: Toward lossless graph condensation via expanding window matching
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 …
a compact counterpart without sacrificing the performance of Graph Neural Networks …
Mitigating label noise on graph via topological sample selection
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 …
graph neural networks (GNNs) can be considerably impaired in practice when the real-world …
Data-augmented curriculum graph neural architecture search under distribution shifts
Graph neural architecture search (NAS) has achieved great success in designing
architectures for graph data processing. However, distribution shifts pose great challenges …
architectures for graph data processing. However, distribution shifts pose great challenges …
Graph principal flow network for conditional graph generation
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 …
graph topology and feature is complicated and the semantic information is hard to capture …
Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification
Graph Neural Architecture Search (GNAS) has achieved superior performance on various
graph-structured tasks. However, existing GNAS studies overlook the applications of GNAS …
graph-structured tasks. However, existing GNAS studies overlook the applications of GNAS …