English
Related papers

Related papers: Learn Beneficial Noise as Graph Augmentation

200 papers

Graph contrastive learning (GCL) has been widely used as an effective self-supervised learning method for graph representation learning. However, how to apply adequate and stable graph augmentation to generating proper views for contrastive…

Machine Learning · Computer Science 2025-01-09 Yanchen Xu , Siqi Huang , Hongyuan Zhang , Xuelong Li

Graph Neural Networks (GNNs) have achieved great success in learning graph representations and thus facilitating various graph-related tasks. However, most GNN methods adopt a supervised learning setting, which is not always feasible in…

Machine Learning · Computer Science 2022-08-16 Hongliang Chi , Yao Ma

Graph Contrastive Learning (GCL) has shown strong promise for unsupervised graph representation learning, yet its effectiveness on heterophilic graphs, where connected nodes often belong to different classes, remains limited. Most existing…

Machine Learning · Computer Science 2026-05-12 Yanan Zhao , Feng Ji , Jingyang Dai , Jiaze Ma , Wee Peng Tay

Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling…

Information Retrieval · Computer Science 2022-05-10 Junliang Yu , Hongzhi Yin , Xin Xia , Tong Chen , Lizhen Cui , Quoc Viet Hung Nguyen

Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data. However, its reliance on data augmentation and its quadratic computational complexity might lead to inconsistency…

Machine Learning · Computer Science 2022-12-12 Hengrui Zhang , Qitian Wu , Yu Wang , Shaofeng Zhang , Junchi Yan , Philip S. Yu

We extend the data augmentation technique PANDA by Li et al. (2018) that regularizes single graph estimation to jointly learning multiple graphical models with various node types in a unified framework. We design two types of noise to…

Methodology · Statistics 2019-05-23 Yinan Li , Xiao Liu , Fang Liu

Graph augmentations are essential for graph contrastive learning. Most existing works use pre-defined random augmentations, which are usually unable to adapt to different input graphs and fail to consider the impact of different nodes and…

Machine Learning · Computer Science 2023-03-28 Yifu Chen , Qianqian Ren , Liu Yong

Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations. Although remarkable progress has been witnessed recently, the success behind GCL is still left somewhat mysterious. In…

Machine Learning · Computer Science 2021-10-27 Yanqiao Zhu , Yichen Xu , Qiang Liu , Shu Wu

We propose the AdaPtive Noise Augmentation (PANDA) procedure to regularize the estimation and inference of generalized linear models (GLMs). PANDA iteratively optimizes the objective function given noise augmented data until convergence to…

Machine Learning · Statistics 2022-04-20 Yinan Li , Fang Liu

We propose an AdaPtive Noise Augmentation (PANDA) technique to regularize the estimation and construction of undirected graphical models. PANDA iteratively optimizes the objective function given the noise augmented data until convergence to…

Machine Learning · Statistics 2019-05-23 Yinan Li , Xiao Liu , Fang Liu

With the prosperity of contrastive learning for visual representation learning (VCL), it is also adapted to the graph domain and yields promising performance. However, through a systematic study of various graph contrastive learning (GCL)…

Machine Learning · Computer Science 2023-11-07 Xiaojun Guo , Yifei Wang , Zeming Wei , Yisen Wang

Graph contrastive learning (GCL) has become a hot topic in the field of graph representation learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation strategies to generate…

Machine Learning · Computer Science 2025-03-28 Jianqing Liang , Xinkai Wei , Min Chen , Zhiqiang Wang , Jiye Liang

Graph Neural Networks (GNNs) are sensitive to structural noise from adversarial attacks or imperfections. Existing graph contrastive learning (GCL) methods typically rely on either random perturbations (e.g., edge dropping) for diversity or…

Machine Learning · Computer Science 2026-02-04 Hao Deng , Zhang Guo , Shuiping Gou , Bo Liu

Graph contrastive learning (GCL) shows great potential in unsupervised graph representation learning. Data augmentation plays a vital role in GCL, and its optimal choice heavily depends on the downstream task. Many GCL methods with…

Machine Learning · Computer Science 2023-05-30 Xin Xiong , Furao Shen , Xiangyu Wang , Jian Zhao

Graph contrastive learning (GCL) has garnered significant attention recently since it learns complex structural information from graphs through self-supervised learning manner. However, prevalent GCL models may suffer from performance…

Machine Learning · Computer Science 2025-04-28 Xiaofan Wei , Binyan Zhang

In the domain of recommendation and collaborative filtering, Graph Contrastive Learning (GCL) has become an influential approach. Nevertheless, the reasons for the effectiveness of contrastive learning are still not well understood. In this…

Information Retrieval · Computer Science 2024-10-01 Chengkai Liu , Jianling Wang , James Caverlee

Teaching Graph Neural Networks (GNNs) to accurately classify nodes under severely noisy labels is an important problem in real-world graph learning applications, but is currently underexplored. Although pairwise training methods have…

Machine Learning · Computer Science 2023-06-06 Xuefeng Du , Tian Bian , Yu Rong , Bo Han , Tongliang Liu , Tingyang Xu , Wenbing Huang , Yixuan Li , Junzhou Huang

Graph contrastive learning (GCL), learning the node representation by contrasting two augmented graphs in a self-supervised way, has attracted considerable attention. GCL is usually believed to learn the invariant representation. However,…

Machine Learning · Computer Science 2024-03-08 Yanhu Mo , Xiao Wang , Shaohua Fan , Chuan Shi

Graph contrastive learning (GCL), as an emerging self-supervised learning technique on graphs, aims to learn representations via instance discrimination. Its performance heavily relies on graph augmentation to reflect invariant patterns…

Machine Learning · Computer Science 2023-06-22 Lu Lin , Jinghui Chen , Hongning Wang

Today, there are two major understandings for graph convolutional networks, i.e., in the spectral and spatial domain. But both lack transparency. In this work, we introduce a new understanding for it -- data augmentation, which is more…

Machine Learning · Computer Science 2020-06-24 Hande Dong , Zhaolin Ding , Xiangnan He , Fuli Feng , Shuxian Bi