50,471 Hits in 5.1 sec

Graph Contrastive Learning with Adaptive Augmentation [article]

Yanqiao Zhu and Yichen Xu and Feng Yu and Qiang Liu and Shu Wu and Liang Wang
2020 arXiv   pre-print
In this paper, we propose a novel graph contrastive representation learning method with adaptive augmentation that incorporates various priors for topological and semantic aspects of the graph.  ...  framework with adaptive augmentation.  ...  To this end, we propose a novel contrastive framework for unsupervised graph representation learning (as shown in Figure 1 ), which we refer to as Graph Contrastive learning with Adaptive augmentation  ... 
arXiv:2010.14945v1 fatcat:grkjpwzitfelbmwfqev4vni4zq

Fairness-Aware Node Representation Learning [article]

Öykü Deniz Köse, Yanning Shen
2021 arXiv   pre-print
To this end, this study addresses fairness issues in graph contrastive learning with fairness-aware graph augmentation designs, through adaptive feature masking and edge deletion.  ...  Despite the success of graph contrastive learning and consequent growing interest, fairness is largely under-explored in the field.  ...  Wang, “Graph contrastive learning with adaptive augmentation,” in Proc. Web Conference (WWW), April 2021. [18] C. Agarwal, H. Lakkaraju*, and M.  ... 
arXiv:2106.05391v1 fatcat:gbzvlecaeresdjn52ec3osvdwe

Graph Data Augmentation for Graph Machine Learning: A Survey [article]

Tong Zhao, Gang Liu, Stephan Günnemann, Meng Jiang
2022 arXiv   pre-print
We provide a GitHub repository ( with a reading list that will be continuously updated.  ...  Next, we introduce recent advances in graph data augmentation, separating by their learning objectives and methodologies.  ...  Contrastive Learning In the past few years, with the rapid development of contrastive learning, several graph contrastive learning methods [You et al., 2021] have been proposed.  ... 
arXiv:2202.08871v1 fatcat:gjf7mgihkfbqdg6cqscflcw6ga

Hyperspectral Image Classification With Contrastive Graph Convolutional Network [article]

Wentao Yu, Sheng Wan, Guangyu Li, Jian Yang, Chen Gong
2022 arXiv   pre-print
In addition, an adaptive graph augmentation technique is designed to flexibly incorporate the spectral-spatial priors of HSI, which helps facilitate the subsequent contrastive representation learning.  ...  To enhance the feature representation ability, in this paper, a GCN model with contrastive learning is proposed to explore the supervision signals contained in both spectral information and spatial relations  ...  [30] developed graph contrastive learning with four types of graph data augmentations, each of which imposed certain prior on graph data and encoded the extent and pattern.  ... 
arXiv:2205.11237v1 fatcat:3ih5erimlfdxlh46ldrhrrfe74

Multi-Level Graph Contrastive Learning [article]

Pengpeng Shao, Tong Liu, Dawei Zhang, Jianhua Tao, Feihu Che, Guohua Yang
2021 arXiv   pre-print
In this paper, we propose a Multi-Level Graph Contrastive Learning (MLGCL) framework for learning robust representation of graph data by contrasting space views of graphs.  ...  Extensive experiments indicate MLGCL achieves promising results compared with the existing state-of-the-art graph representation learning methods on seven datasets.  ...  GPT [12] ), contrastive learning coupled with GNNs graph representation learning becomes an open task.  ... 
arXiv:2107.02639v1 fatcat:c7zsvxgiczcj7f5evasefn4yue

Spatio-Temporal Graph Contrastive Learning [article]

Xu Liu, Yuxuan Liang, Yu Zheng, Bryan Hooi, Roger Zimmermann
2021 arXiv   pre-print
To alleviate these limitations, an intuitive idea is to use the popular data augmentation and contrastive learning techniques.  ...  In this paper, we propose a Spatio-Temporal Graph Contrastive Learning framework (STGCL) to tackle these issues.  ...  Graph Contrastive Learning framework (STGCL).  ... 
arXiv:2108.11873v1 fatcat:ktkpm3m33fdr5lxglcmqcijpce

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection [article]

Vibashan VS, Poojan Oza, Vishal M. Patel
2022 arXiv   pre-print
These object instance relations are modelled using an Instance Relation Graph (IRG) network, which are then used to guide the contrastive representation learning.  ...  More precisely, we design a novel contrastive loss to enhance the target representations by exploiting the objects relations for a given target domain input.  ...  Conclusion In this work, we presented a novel approach for source-free domain adaptive detection using graph-guided contrastive learning.  ... 
arXiv:2203.15793v2 fatcat:lwijjg6zmfc2hmah3yb6q7udj4

Neural Graph Matching for Pre-training Graph Neural Networks [article]

Yupeng Hou, Binbin Hu, Wayne Xin Zhao, Zhiqiang Zhang, Jun Zhou, Ji-Rong Wen
2022 arXiv   pre-print
In this way, we can learn adaptive representations for a given graph when paired with different graphs, and both node- and graph-level characteristics are naturally considered in a single pre-training  ...  Focusing on a pair of graphs, we propose to learn structural correspondences between them via neural graph matching, consisting of both intra-graph message passing and inter-graph message passing.  ...  Contrastive Learning with Adaptive Graph Representations Contrastive learning is a commonly used technique to learn with augmented graph views in pairs [28] .  ... 
arXiv:2203.01597v1 fatcat:fq6zrtbbcvdd5dgcxp2cgwgazy

Graph Contrastive Learning Automated [article]

Yuning You, Tianlong Chen, Yang Shen, Zhangyang Wang
2021 arXiv   pre-print
Among many, graph contrastive learning (GraphCL) has emerged with promising representation learning performance.  ...  Self-supervised learning on graph-structured data has drawn recent interest for learning generalizable, transferable and robust representations from unlabeled graphs.  ...  by JOAO, we design a new augmentation-aware projection head for graph contrastive learning.  ... 
arXiv:2106.07594v2 fatcat:kkgtxgxwqjfnfhoqnmg4bsjqu4

Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning [article]

Jun Hu, Shengsheng Qian, Quan Fang, Changsheng Xu
2021 arXiv   pre-print
This paper proposes an efficient yet effective end-to-end framework, namely Contrastive Adaptive Propagation Graph Neural Networks (CAPGNN), to address these issues by combining Personalized PageRank and  ...  In addition, we leverage self-supervised learning techniques and design a negative-free entropy-aware contrastive loss to explicitly take advantage of unlabeled data for training.  ...  Our contrastive loss constrains our GNN model to learn consistent semantics for the same vertex across multiple randomly augmented views of a graph.  ... 
arXiv:2112.01110v1 fatcat:yaviuqnj3zdmddeo6i3rhz5vb4

Adversarial Graph Contrastive Learning with Information Regularization [article]

Shengyu Feng, Baoyu Jing, Yada Zhu, Hanghang Tong
2022 arXiv   pre-print
Contrastive learning is an effective unsupervised method in graph representation learning. Recently, the data augmentation based contrastive learning method has been extended from images to graphs.  ...  Unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and much harder to provide high-quality contrastive samples, which are the key to the performance of contrastive  ...  Graph Contrastive learning with Adaptive augmentation (GCA) [41] introduces an adaptive data augmentation method which perturbs both the node features and edges according to their importance, and it  ... 
arXiv:2202.06491v3 fatcat:dbunnvzl6zeyfdfshhivhjynbi

An Empirical Study of Graph Contrastive Learning [article]

Yanqiao Zhu, Yichen Xu, Qiang Liu, Shu Wu
2021 arXiv   pre-print
Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations.  ...  Our empirical studies suggest a set of general receipts for effective GCL, e.g., simple topology augmentations that produce sparse graph views bring promising performance improvements; contrasting modes  ...  Graph Contrastive Learning (GCL) adapts the idea of CL to the graph domain.  ... 
arXiv:2109.01116v2 fatcat:kjfrkg26tbfxhoiomx2mdgao5y

GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction [article]

Shuangli Li, Jingbo Zhou, Tong Xu, Dejing Dou, Hui Xiong
2021 arXiv   pre-print
Though graph contrastive learning (GCL) methods have achieved extraordinary performance with insufficient labeled data, most focused on designing data augmentation schemes for general graphs.  ...  However, the fundamental property of a molecule could be altered with the augmentation method (like random perturbation) on molecular graphs.  ...  to learn the representations of both graphs adaptively.  ... 
arXiv:2109.11730v1 fatcat:l2chcnrs45bexehlgvry6a2mhm

Graph Self-Supervised Learning: A Survey [article]

Yixin Liu, Ming Jin, Shirui Pan, Chuan Zhou, Yu Zheng, Feng Xia, Philip S. Yu
2022 arXiv   pre-print
Deep learning on graphs has attracted significant interests recently.  ...  Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data.  ...  In 2021, more advanced techniques are integrated with graph SSL, such as adaptive augmentation (GCA [69] ), automatic machine learning (JOAO [70] ), and adversarial augmentation (AD-GCL [75] ). when  ... 
arXiv:2103.00111v4 fatcat:y3zfg4ennnbnhhvmujd5rvltty

RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation [article]

Yijun Tian, Chuxu Zhang, Zhichun Guo, Chao Huang, Ronald Metoyer, Nitesh V. Chawla
2022 arXiv   pre-print
We also introduce a graph contrastive augmentation strategy to extract informative graph knowledge in a self-supervised manner.  ...  Finally, we design a joint objective function of recommendation and contrastive learning to optimize the model.  ...  Graph Contrastive Augmentation Since the above objective function only considers explicit and supervised information in the URI-Graph, we further introduce a graph contrastive augmentation strategy to  ... 
arXiv:2205.14005v1 fatcat:s2zvy7ohhfeklhf72u4mxhz4q4
« Previous Showing results 1 — 15 out of 50,471 results