Graph structure learning with variational information bottleneck
Abstract Graph Neural Networks (GNNs) have shown promising results on a broad spectrum
of applications. Most empirical studies of GNNs directly take the observed graph as input …
of applications. Most empirical studies of GNNs directly take the observed graph as input …
Prototypical graph contrastive learning
Graph-level representations are critical in various real-world applications, such as predicting
the properties of molecules. However, in practice, precise graph annotations are generally …
the properties of molecules. However, in practice, precise graph annotations are generally …
Contrast everything: A hierarchical contrastive framework for medical time-series
Y Wang, Y Han, H Wang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Contrastive representation learning is crucial in medical time series analysis as it alleviates
dependency on labor-intensive, domain-specific, and scarce expert annotations. However …
dependency on labor-intensive, domain-specific, and scarce expert annotations. However …
Ma-gcl: Model augmentation tricks for graph contrastive learning
Contrastive learning (CL), which can extract the information shared between different
contrastive views, has become a popular paradigm for vision representation learning …
contrastive views, has become a popular paradigm for vision representation learning …
Instance-specific feature propagation for referring segmentation
Referring segmentation aims to generate a segmentation mask for the target instance
indicated by a natural language expression. There are typically two kinds of existing …
indicated by a natural language expression. There are typically two kinds of existing …
Searching large neighborhoods for integer linear programs with contrastive learning
Abstract Integer Linear Programs (ILPs) are powerful tools for modeling and solving a large
number of combinatorial optimization problems. Recently, it has been shown that Large …
number of combinatorial optimization problems. Recently, it has been shown that Large …
Ricci curvature-based graph sparsification for continual graph representation learning
Memory replay, which stores a subset of historical data from previous tasks to replay while
learning new tasks, exhibits state-of-the-art performance for various continual learning …
learning new tasks, exhibits state-of-the-art performance for various continual learning …
Knowledge-aware deep framework for collaborative skin lesion segmentation and melanoma recognition
Deep learning techniques have shown their superior performance in dermatologist clinical
inspection. Nevertheless, melanoma diagnosis is still a challenging task due to the difficulty …
inspection. Nevertheless, melanoma diagnosis is still a challenging task due to the difficulty …
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 …
Minimum entropy principle guided graph neural networks
Graph neural networks (GNNs) are now the mainstream method for mining graph-structured
data and learning low-dimensional node-and graph-level embeddings to serve downstream …
data and learning low-dimensional node-and graph-level embeddings to serve downstream …