Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Loss of the APP regulator RHBDL4 preserves memory in an Alzheimer's disease mouse model.

bioRxiv : the preprint server for biology·2024

Same author

Integration analysis of lncRNA and mRNA expression data identifies DOCK4 as a potential biomarker for elderly osteoporosis.

BMC medical genomics·2024

Same author

A systematic review and meta-analysis of the anti-tumor effects of Paeoniae Radix Rubra in animal models.

Journal of ethnopharmacology·2024

Same author

Resilience conferred by APOE-R136S: a defense bestowed by nature to combat Alzheimer's disease.

Signal transduction and targeted therapy·2024

Same author

Enhanced NMDA receptor pathway and glutamate transmission in the hippocampal dentate gyrus mediate the spatial learning and memory impairment of obese rats.

Pflugers Archiv : European journal of physiology·2024

Same author

Benzodiazepines and mortality: Consideration of potential confounders.

Pain practice : the official journal of World Institute of Pain·2024

Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026

Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 5, 2025

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Revisiting Initializing Then Refining: An Incomplete and Missing Graph Imputation Network.

Wenxuan Tu, Bin Xiao, Xinwang Liu

IEEE Transactions on Neural Networks and Learning Systems

|January 12, 2024

Summary

This summary is machine-generated.

This study introduces a novel graph imputation network (RITR) to address missing data in graphs. The method effectively handles both incomplete and missing attributes, outperforming existing techniques in experiments.

More Related Videos

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Related Experiment Videos

Last Updated: Jul 5, 2025

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Area of Science:

Graph Machine Learning
Data Mining
Network Science

Background:

Graph data is prevalent in applications like recommendation systems and social network analysis.
Graph data often suffers from missing attributes due to privacy or copyright issues, categorized as attribute-incomplete or attribute-missing.
Existing graph imputation methods do not address scenarios with both types of missing data simultaneously.

Purpose of the Study:

To develop a novel graph imputation network (RITR) capable of handling hybrid-absent graphs (both attribute-incomplete and attribute-missing).
To introduce an initializing-then-refining imputation criterion for effective graph data completion.
To provide the first end-to-end unsupervised framework for hybrid-absent graph imputation.

Main Methods:

For attribute-incomplete samples: initialize with Gaussian noise, then refine using a structure-attribute consistency constraint.
For attribute-missing samples: initialize with structure embeddings, then refine by aggregating information from attribute-incomplete samples via a dynamic affinity structure.
The RITR network employs an initializing-then-refining strategy for both data types.

Main Results:

RITR successfully imputes both attribute-incomplete and attribute-missing graph data.
Experiments on six datasets demonstrate that RITR consistently outperforms state-of-the-art competitors.
The proposed method achieves superior performance in handling hybrid-absent graphs.

Conclusions:

The developed RITR network is an effective end-to-end unsupervised framework for hybrid-absent graph imputation.
RITR addresses a significant gap in existing graph imputation techniques.
The method shows strong potential for real-world applications involving incomplete graph data.