Papers Node Classification
“Node Classification” 태그가 달린 논문 2,077편 · 필터 해제
GRE^2-MDCL: Graph Representation Embedding Enhanced via Multidimensional Contrastive Learning
Graph representation learning has emerged as a powerful tool for preserving graph topology when mapping nodes to vector representations, enabling various downstream tasks such as node classification and community detecti…
Community DetectionContrastive LearningGraph Neural NetworkGraph Representation Learning+2Virtual Node Generation for Node Classification in Sparsely-Labeled Graphs
In the broader machine learning literature, data-generation methods demonstrate promising results by generating additional informative training examples via augmenting sparse labels. Such methods are less studied in grap…
Graph LearningMeta-LearningNode ClassificationSelf-Supervised LearningMixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
Heterophilous graphs, where dissimilar nodes tend to connect, pose a challenge for graph neural networks (GNNs). Increasing the GNN depth can expand the scope (i.e., receptive field), potentially finding homophily from t…
Node ClassificationInformation Extraction from Visually Rich Documents Using Directed Weighted Graph Neural Network
This paper presents a novel approach to information extraction (IE) from visually rich documents (VRD) by employing a directed weighted graph representation to capture relationships among various VRD components. In contr…
Document Layout Analysisdocument understandingGraph Neural NetworkInformation Retrieval+2Graffin: Stand for Tails in Imbalanced Node Classification
Graph representation learning (GRL) models have succeeded in many scenarios. Real-world graphs have imbalanced distribution, such as node labels and degrees, which leaves a critical challenge to GRL. Imbalanced inputs ca…
ClassificationData AugmentationGraph Representation LearningNode Classification+1Generalized Learning of Coefficients in Spectral Graph Convolutional Networks
Spectral Graph Convolutional Networks (GCNs) have gained popularity in graph machine learning applications due, in part, to their flexibility in specification of network propagation rules. These propagation rules are oft…
Node ClassificationCUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks
In this work, we study the influence of domain-specific characteristics when defining a meaningful notion of predictive uncertainty on graph data. Previously, the so-called Graph Posterior Network (GPN) model has been pr…
Node ClassificationUncertainty QuantificationA Survey on Signed Graph Embedding: Methods and Applications
A signed graph (SG) is a graph where edges carry sign information attached to it. The sign of a network can be positive, negative, or neutral. A signed network is ubiquitous in a real-world network like social networks, …
Community DetectionGraph EmbeddingLink PredictionNetwork Embedding+2Self-Directed Learning of Convex Labelings on Graphs
We study the problem of learning the clusters of a given graph in the self-directed learning setup. This learning setting is a variant of online learning, where rather than an adversary determining the sequence in which …
Node ClassificationHound: Hunting Supervision Signals for Few and Zero Shot Node Classification on Text-attributed Graph
Text-attributed graph (TAG) is an important type of graph structured data with text descriptions for each node. Few- and zero-shot node classification on TAGs have many applications in fields such as academia and social …
NegationNode ClassificationTAGText MatchingReproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
In this study, we undertake a reproducibility analysis of 'Learning Fair Graph Representations Via Automated Data Augmentations' by Ling et al. (2022). We assess the validity of the original claims focused on node classi…
FairnessLink PredictionNode ClassificationSympGNNs: Symplectic Graph Neural Networks for identifiying high-dimensional Hamiltonian systems and node classification
Existing neural network models to learn Hamiltonian systems, such as SympNets, although accurate in low-dimensions, struggle to learn the correct dynamics for high-dimensional many-body systems. Herein, we introduce Symp…
Node ClassificationSFR-GNN: Simple and Fast Robust GNNs against Structural Attacks
Graph Neural Networks (GNNs) have demonstrated commendable performance for graph-structured data. Yet, GNNs are often vulnerable to adversarial structural attacks as embedding generation relies on graph topology. Existin…
Contrastive LearningGraph Neural NetworkNode ClassificationGSTAM: Efficient Graph Distillation with Structural Attention-Matching
Graph distillation has emerged as a solution for reducing large graph datasets to smaller, more manageable, and informative ones. Existing methods primarily target node classification, involve computationally intensive p…
ClassificationGraph ClassificationNode ClassificationExploring the Potential of Large Language Models for Heterophilic Graphs
Large language models (LLMs) have presented significant opportunities to enhance various machine learning applications, including graph neural networks (GNNs). By leveraging the vast open-world knowledge within LLMs, we …
Node ClassificationWorld KnowledgeRoCP-GNN: Robust Conformal Prediction for Graph Neural Networks in Node-Classification
Graph Neural Networks (GNNs) have emerged as powerful tools for predicting outcomes in graph-structured data. However, a notable limitation of GNNs is their inability to provide robust uncertainty estimates, which underm…
Conformal PredictionLink PredictionNode ClassificationPrediction+1LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings
Zero-shot graph machine learning, especially with graph neural networks (GNNs), has garnered significant interest due to the challenge of scarce labeled data. While methods like self-supervised learning and graph prompt …
Language ModellingLink PredictionNode ClassificationPrompt Learning+2Slicing Input Features to Accelerate Deep Learning: A Case Study with Graph Neural Networks
As graphs grow larger, full-batch GNN training becomes hard for single GPU memory. Therefore, to enhance the scalability of GNN training, some studies have proposed sampling-based mini-batch training and distributed grap…
GPUGraph LearningNode ClassificationLeveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts
Heterophilic Graph Neural Networks (HGNNs) have shown promising results for semi-supervised learning tasks on graphs. Notably, most real-world heterophilic graphs are composed of a mixture of nodes with different neighbo…
Data AugmentationNode ClassificationFederated Graph Learning with Structure Proxy Alignment
Federated Graph Learning (FGL) aims to learn graph learning models over graph data distributed in multiple data owners, which has been applied in various applications such as social recommendation and financial fraud det…
Federated LearningFraud DetectionGraph LearningNode Classification