Works (8)
Updated: October 21st, 2024 05:00
2024 conference paper
Data Quality-aware Graph Machine Learning
Wang, Y., Ding, K., Liu, X., Kang, J., Rossi, R., & Derr, T. (2024, October 21).
Source: ORCID
Added: October 20, 2024
2024 conference paper
Linear-Time Graph Neural Networks for Scalable Recommendations
Zhang, J., Xue, R., Fan, W., Xu, X., Li, Q., Pei, J., & Liu, X. (2024, May 13).
open access via arxiv.org (repository)
Source: ORCID
Added: May 15, 2024
2024 journal article
Manufacturing service capability prediction with Graph Neural Networks
JOURNAL OF MANUFACTURING SYSTEMS, 74, 291–301.
author keywords: Node classification; Link prediction; Graph neural network; Manufacturing service capability; Manufacturing Service Knowledge Graph
UN Sustainable Development Goal Categories
9. Industry, Innovation and Infrastructure
(Web of Science)
12. Responsible Consumption and Production
(Web of Science)
Sources: ORCID, Web Of Science, NC State University Libraries
Added: April 8, 2024
2023 article
Enhancing Graph Representations Learning with Decorrelated Propagation
PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, pp. 1466–1476.
author keywords: Graph Neural Networks; Over-correlation; Over-smoothing; Semi-supervised node classification
TL;DR:
A decorrelated propagation scheme (DeProp) is proposed as a fundamental component to decorrelate the feature learning in GNN models, which achieves feature decorrelation at the propagation step and can be used to solve over-smoothing and over-correlation problems simultaneously and significantly outperform state-of-the-art methods on missing feature settings.
(via Semantic Scholar)
Sources: ORCID, Web Of Science, NC State University Libraries
Added: August 5, 2023
2023 article
How does the Memorization of Neural Networks Impact Adversarial Robust Models?
PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, pp. 2801–2812.
author keywords: Adversarial example; robustness; over-parameterization
TL;DR:
Benign Adversarial Training (BAT) is proposed which can facilitate adversarial training to avoid fitting "harmful" atypical samples and fit as more "benign" atYPical samples as possible and can achieve better clean accuracy vs. robustness trade-off than baseline methods, in benchmark datasets for image classification.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
3. Good Health and Well-being
(Web of Science)
Sources: ORCID, Web Of Science, NC State University Libraries
Added: August 5, 2023
2023 article
Large-Scale Graph Neural Networks: The Past and New Frontiers
PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, pp. 5835–5836.
author keywords: Graph Neural Networks; Large-scale Graphs; Scalability
TL;DR:
This tutorial aims to provide a systematic and comprehensive understanding of the challenges and state-of-the-art techniques for scaling GNNs, and to explore new ideas and developments in this rapidly evolving field.
(via Semantic Scholar)
Sources: ORCID, Web Of Science, NC State University Libraries
Added: August 5, 2023
2022 article
Imbalanced Adversarial Training with Reweighting
2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), pp. 1209–1214.
author keywords: model robustness; imbalanced data; adversarial training; reweighting
TL;DR:
The poor data separability is one key reason causing this strong tension between under-represented and well-represented classes and the Separable Reweighted Adversarial Training (SRAT) framework is proposed to facilitate adversarial training under imbalanced scenarios, by learning more separable features for different classes.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
3. Good Health and Well-being
(Web of Science)
Sources: Web Of Science, NC State University Libraries
Added: May 22, 2023
2022 journal article
Trustworthy AI: A Computational Perspective
ACM Transactions on Intelligent Systems and Technology.
TL;DR:
A comprehensive appraisal of trustworthy AI from a computational perspective to help readers understand the latest technologies for achieving trustworthy AI and focuses on six of the most crucial dimensions.
(via Semantic Scholar)
Source: ORCID
Added: April 3, 2023
Citation Index includes data from a number of different sources. If you have questions about the sources of data in the Citation Index or need a set of data which is free to re-distribute, please contact us.
Certain data included herein are derived from the Web of Science© and InCites© (2024) of Clarivate Analytics. All rights reserved. You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.