Papers Graph Representation Learning
“Graph Representation Learning” 태그가 달린 논문 1,123편 · 필터 해제
Cycle Invariant Positional Encoding for Graph Representation Learning
Cycles are fundamental elements in graph-structured data and have demonstrated their effectiveness in enhancing graph learning models. To encode such information into a graph learning framework, prior works often extract…
Graph LearningGraph Representation LearningRepresentation LearningHGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding
Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revea…
Fine-Grained Visual RecognitionGraph Representation LearningRepresentation LearningCareful Selection and Thoughtful Discarding: Graph Explicit Pooling Utilizing Discarded Nodes
Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning. Existing graph pooling methods commonly consist of two stages: selectin…
Graph Representation LearningRepresentation LearningCross-View Graph Consistency Learning for Invariant Graph Representations
Graph representation learning is fundamental for analyzing graph-structured data. Exploring invariant graph representations remains a challenge for most existing graph representation learning methods. In this paper, we p…
AttributeData AugmentationGraph Representation LearningLink Prediction+1Classification of developmental and brain disorders via graph convolutional aggregation
While graph convolution based methods have become the de-facto standard for graph representation learning, their applications to disease prediction tasks remain quite limited, particularly in the classification of neurod…
Disease PredictionGraph Representation LearningGraph SamplingRepresentation LearningTopology Only Pre-Training: Towards Generalised Multi-Domain Graph Models
The principal benefit of unsupervised representation learning is that a pre-trained model can be fine-tuned where data or labels are scarce. Existing approaches for graph representation learning are domain specific, main…
Contrastive LearningGraph LearningGraph Representation LearningRepresentation Learning+1Temporal Graph Representation Learning with Adaptive Augmentation Contrastive
Temporal graph representation learning aims to generate low-dimensional dynamic node embeddings to capture temporal information as well as structural and property information. Current representation learning methods for …
Contrastive LearningGraph Representation LearningRepresentation LearningHDGL: A hierarchical dynamic graph representation learning model for brain disorder classification
The human brain can be considered as complex networks, composed of various regions that continuously exchange their information with each other, forming the brain network graph, from which nodes and edges are extracted u…
Functional ConnectivityGraph Representation LearningRepresentation LearningCalibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs
As a powerful framework for graph representation learning, Graph Neural Networks (GNNs) have garnered significant attention in recent years. However, to the best of our knowledge, there has been no formal analysis of the…
Graph Representation LearningNode ClassificationRepresentation LearningGraph Representation Learning for Infrared and Visible Image Fusion
Infrared and visible image fusion aims to extract complementary features to synthesize a single fused image. Many methods employ convolutional neural networks (CNNs) to extract local features due to its translation invar…
Graph Representation LearningInfrared And Visible Image FusionRepresentation LearningDyTSCL: Dynamic graph representation via tempo-structural contrastive learning
With the massive growth of graph-structured data, extensive research has focused on graph representation learning. Recently, graph representation learning frameworks have made great efforts toward dynamic graph learning.…
Contrastive LearningGraph LearningGraph Representation LearningRepresentation LearningDiversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning
Graph pooling methods have been widely used on downsampling graphs, achieving impressive results on multiple graph-level tasks like graph classification and graph generation. An important line called node dropping poolin…
Graph ClassificationGraph GenerationGraph Representation LearningRepresentation LearningPrivacy-preserving design of graph neural networks with applications to vertical federated learning
The paradigm of vertical federated learning (VFL), where institutions collaboratively train machine learning models via combining each other's local feature or label information, has achieved great success in application…
Federated LearningGraph Representation LearningManagementPrivacy Preserving+2Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
Invariant graph representation learning aims to learn the invariance among data from different environments for out-of-distribution generalization on graphs. As the graph environment partitions are usually expensive to o…
Graph LearningGraph Representation LearningOut-of-Distribution GeneralizationRepresentation LearningA Causal Disentangled Multi-Granularity Graph Classification Method
Graph data widely exists in real life, with large amounts of data and complex structures. It is necessary to map graph data to low-dimensional embedding. Graph classification, a critical graph task, mainly relies on iden…
ClassificationDisentanglementGraph ClassificationGraph Representation Learning+1Knowledge-Induced Medicine Prescribing Network for Medication Recommendation
Extensive adoption of electronic health records (EHRs) offers opportunities for their use in various downstream clinical analyses. To accomplish this purpose, enriching an EHR cohort with external knowledge (e.g., standa…
Graph Representation LearningKnowledge GraphsRepresentation LearningUniMAP: Universal SMILES-Graph Representation Learning
Molecular representation learning is fundamental for many drug related applications. Most existing molecular pre-training models are limited in using single molecular modality, either SMILES or graph representation. To e…
Graph MatchingGraph Representation LearningMolecular Property Predictionmolecular representation+2Spectral-Aware Augmentation for Enhanced Graph Representation Learning
Graph Contrastive Learning (GCL) has demonstrated remarkable effectiveness in learning representations on graphs in recent years. To generate ideal augmentation views, the augmentation generation methods should preserve …
Contrastive LearningGraph Representation LearningRepresentation LearningGraph AI in Medicine
In clinical artificial intelligence (AI), graph representation learning, mainly through graph neural networks (GNNs), stands out for its capability to capture intricate relationships within structured clinical datasets. …
Decision MakingGraph Representation LearningKnowledge GraphsRepresentation LearningEnhancing the Performance of Automated Grade Prediction in MOOC using Graph Representation Learning
In recent years, Massive Open Online Courses (MOOCs) have gained significant traction as a rapidly growing phenomenon in online learning. Unlike traditional classrooms, MOOCs offer a unique opportunity to cater to a dive…
Graph EmbeddingGraph Representation LearningRepresentation Learning