paper-with-me

Papers Dynamic Node Classification

“Dynamic Node Classification” 태그가 달린 논문 10편 · 필터 해제

Predict Confidently, Predict Right: Abstention in Dynamic Graph Learning

2025-01-14 · Jayadratha Gayen, Himanshu Pal, Naresh Manwani, Charu Sharma

Many real-world systems can be modeled as dynamic graphs, where nodes and edges evolve over time, requiring specialized models to capture their evolving dynamics in risk-sensitive applications effectively. Temporal graph…

Abstention PredictionDynamic Link PredictionDynamic Node ClassificationGraph Learning+3

Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification

2024-11-06 · Benedict Aaron Tjandra, Federico Barbero, Michael Bronstein

Despite the successful application of Temporal Graph Networks (TGNs) for tasks such as dynamic node classification and link prediction, they still perform poorly on the task of dynamic node affinity prediction -- where t…

Dynamic Node ClassificationLink PredictionNode ClassificationPrediction

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

2024-08-13 · Dongyuan Li, Shiyin Tan, Ying Zhang, Ming Jin 외

Dynamic graph learning aims to uncover evolutionary laws in real-world systems, enabling accurate social recommendation (link prediction) or early detection of cancer cells (classification). Inspired by the success of st…

Dynamic Link PredictionDynamic Node ClassificationGraph LearningLanguage Modeling+5

Dynamic Spiking Framework for Graph Neural Networks

2023-12-15 · Nan Yin, Mengzhu Wang, Zhenghan Chen, Giulia De Masi 외

The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks (GNNs) is gradually attracting attention due to the low power consumption and high efficiency in processing the non-Euclidean data represented b…

Dynamic Node ClassificationGraph Representation LearningNode ClassificationRepresentation Learning

Less Can Be More: Unsupervised Graph Pruning for Large-scale Dynamic Graphs

2023-05-18 · Jintang Li, Sheng Tian, Ruofan Wu, Liang Zhu 외

The prevalence of large-scale graphs poses great challenges in time and storage for training and deploying graph neural networks (GNNs). Several recent works have explored solutions for pruning the large original graph i…

Dynamic Node ClassificationNode Classification

Towards Better Dynamic Graph Learning: New Architecture and Unified Library

2023-03-23 · NeurIPS 2023 11 · Le Yu, Leilei Sun, Bowen Du, Weifeng Lv

We propose DyGFormer, a new Transformer-based architecture for dynamic graph learning. DyGFormer is conceptually simple and only needs to learn from nodes' historical first-hop interactions by: (1) a neighbor co-occurren…

Dynamic Link PredictionDynamic Node ClassificationGraph LearningLink Prediction+1

EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning

2023-03-22 · Chao Chen, Haoyu Geng, Nianzu Yang, Xiaokang Yang 외

Dynamic graphs arise in various real-world applications, and it is often welcomed to model the dynamics directly in continuous time domain for its flexibility. This paper aims to design an easy-to-use pipeline (termed as…

Dynamic Link PredictionDynamic Node ClassificationFraud DetectionGraph Learning+4

DyG2Vec: Efficient Representation Learning for Dynamic Graphs

2022-10-30 · Mohammad Ali Alomrani, Mahdi Biparva, Yingxue Zhang, Mark Coates

Temporal graph neural networks have shown promising results in learning inductive representations by automatically extracting temporal patterns. However, previous works often rely on complex memory modules or inefficient…

Dynamic Link PredictionDynamic Node ClassificationLink PredictionRepresentation Learning+1

GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs

2021-10-11 · Yucai Fan, Yuhang Yao, Carlee Joe-Wong

Graph Convolutional Networks (GCNs) are a popular method from graph representation learning that have proved effective for tasks like node classification tasks. Although typical GCN models focus on classifying nodes with…

ClassificationDynamic Node ClassificationGraph Representation LearningNode Classification+1

ConTIG: Continuous Representation Learning on Temporal Interaction Graphs

2021-09-27 · Xu Yan, Xiaoliang Fan, Peizhen Yang, Zonghan Wu 외

Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG disc…

Dynamic Node ClassificationLink PredictionNode ClassificationRepresentation Learning
1–10 / 10