Search Results for author: Ning Gui

Found 9 papers, 5 papers with code

Multi-View Graph Representation Learning Beyond Homophily

1 code implementation15 Apr 2023 Bei Lin, You Li, Ning Gui, Zhuopeng Xu, Zhiwu Yu

However, partially due to the irregular non-Euclidean data in graphs, the pretext tasks are generally designed under homophily assumptions and cornered in the low-frequency signals, which results in significant loss of other signals, especially high-frequency signals widespread in graphs with heterophily.

Graph Representation Learning Self-Supervised Learning

Data Imputation with Iterative Graph Reconstruction

no code implementations6 Dec 2022 Jiajun Zhong, Weiwei Ye, Ning Gui

Effective data imputation demands rich latent ``structure" discovery capabilities from ``plain" tabular data.

Graph Generation Graph Reconstruction +1

A-SFS: Semi-supervised Feature Selection based on Multi-task Self-supervision

no code implementations19 Jul 2022 Zhifeng Qiu, Wanxin Zeng, Dahua Liao, Ning Gui

Guided by the integrated information from the multi-self-supervised learning model, a batch-attention mechanism is designed to generate feature weights according to batch-based feature selection patterns to alleviate the impacts introduced by a handful of noisy data.

feature selection Self-Supervised Learning

An Embedded Feature Selection Framework for Control

1 code implementation19 Jun 2022 Jiawen Wei, Fangyuan Wang, Wanxin Zeng, Wenwei Lin, Ning Gui

Reducing sensor requirements while keeping optimal control performance is crucial to many industrial control applications to achieve robust, low-cost, and computation-efficient controllers.

feature selection

Graph Representation Learning Beyond Node and Homophily

1 code implementation3 Mar 2022 You Li, Bei Lin, Binli Luo, Ning Gui

Unsupervised graph representation learning aims to distill various graph information into a downstream task-agnostic dense vector embedding.

Edge Classification Graph Embedding +2

Pair-view Unsupervised Graph Representation Learning

no code implementations11 Dec 2020 You Li, Binli Luo, Ning Gui

Low-dimension graph embeddings have proved extremely useful in various downstream tasks in large graphs, e. g., link-related content recommendation and node classification tasks, etc.

Graph Representation Learning Link Prediction +1

AFS: An Attention-based mechanism for Supervised Feature Selection

1 code implementation28 Feb 2019 Ning Gui, Danni Ge, Ziyin Hu

AFS consists of two detachable modules: an at-tention module for feature weight generation and a learning module for the problem modeling.

Binary Classification feature selection

The Missing Ones: Key Ingredients Towards Effective Ambient Assisted Living Systems

no code implementations12 Jan 2014 Hong Sun, Vincenzo De Florio, Ning Gui, Chris Blondia

Challenges in increasing the human participation in ambient assisted living are discussed in this paper and solutions to meet those challenges are also proposed.

Cannot find the paper you are looking for? You can Submit a new open access paper.