paper-with-me

Papers

Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks

2021-06-24 · Jiaqing Xie, Rex Ying

Structural features are important features in a geometrical graph. Although there are some correlation analysis of features based on covariance, there is no relevant research on structural feature correlation analysis with graph neural networks. In this paper, we introuduce graph feature to feature (Fea2Fea) prediction pipelines in a low dimensional space to explore some preliminary results on structural feature correlation, which is based on graph neural network. The results show that there exists high correlation between some of the structural features. An irredundant feature combination with initial node features, which is filtered by graph neural network has improved its classification accuracy in some graph-based tasks. We compare differences between concatenation methods on connecting embeddings between features and show that the simplest is the best. We generalize on the synthetic geometric graphs and certify the results on prediction difficulty between structural features.

📄 PDF Abstract BibTeX arXiv:2106.13061

Code (1)

JIAQING-XIE/Fea2Fea pytorch

Tasks

Feature CorrelationGraph ClassificationGraph Neural NetworkNode ClassificationStructual Feature Correlation

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Adaptive Structural Similarity Preserving for Unsupervised Cross Modal Hashing

2022-07-09 · Liang Li, Baihua Zheng, Weiwei Sun

Cross-modal hashing is an important approach for multimodal data management and application. Existing unsupervised cross-modal hashing algorithms mainly rely on data features in pre-trained models to mine their similarit…

ManagementRepresentation Learning

Exploring Correlations in Multiple Facial Attributes through Graph Attention Network

2018-10-22 · Yan Zhang, Li Sun

Estimating multiple attributes from a single facial image gives comprehensive descriptions on the high level semantics of the face. It is naturally regarded as a multi-task supervised learning problem with a single deep …

AttributeGraph AttentionMulti-Task Learning

SEHFS: Structural Entropy-Guided High-Order Correlation Learning for Multi-View Multi-Label Feature Selection

2026-03-03 · Cheng Peng, Yonghao Li, Wanfu Gao, Jie Wen 외 arxiv

In recent years, multi-view multi-label learning (MVML) has attracted extensive attention due to its close alignment to real-world scenarios. Information-theoretic methods have gained prominence for learning nonlinear co…

Multi-Label Learning

Transformer-based Dual Relation Graph for Multi-label Image Recognition

2021-10-10 · ICCV 2021 10 · Jiawei Zhao, Ke Yan, Yifan Zhao, Xiaowei Guo 외

The simultaneous recognition of multiple objects in one image remains a challenging task, spanning multiple events in the recognition field such as various object scales, inconsistent appearances, and confused inter-clas…

Multi-Label ClassificationMulti-Label Image RecognitionRelation

Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization

2023-06-28 · Ling Yang, Jiayi Zheng, Heyuan Wang, Zhongyi Liu 외

Out-of-distribution (OOD) graph generalization are critical for many real-world applications. Existing methods neglect to discard spurious or noisy features of inputs, which are irrelevant to the label. Besides, they mai…

Graph LearningOut-of-Distribution Generalization