English
Related papers

Related papers: Learn Beneficial Noise as Graph Augmentation

200 papers

Learning with noisy labels has been studied to address incorrect label annotations in real-world applications. In this paper, we present ChiMera, a two-stage learning-from-noisy-labels framework based on semi-supervised learning, developed…

Computational Engineering, Finance, and Science · Computer Science 2023-10-10 Zixuan Liu , Xin Zhang , Junjun He , Dan Fu , Dimitris Samaras , Robby Tan , Xiao Wang , Sheng Wang

Advanced graph neural networks have shown great potentials in graph classification tasks recently. Different from node classification where node embeddings aggregated from local neighbors can be directly used to learn node labels, graph…

Machine Learning · Computer Science 2022-03-16 Hao Jia , Junzhong Ji , Minglong Lei

Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so…

Computer Vision and Pattern Recognition · Computer Science 2022-01-24 Xiao Wang , Guo-Jun Qi

As trustworthy AI continues to advance, the fairness issue in recommendations has received increasing attention. A recommender system is considered unfair when it produces unequal outcomes for different user groups based on user-sensitive…

Artificial Intelligence · Computer Science 2024-10-24 Wei Chen , Meng Yuan , Zhao Zhang , Ruobing Xie , Fuzhen Zhuang , Deqing Wang , Rui Liu

Contrastive learning (CL) has become the de-facto learning paradigm in self-supervised learning on graphs, which generally follows the "augmenting-contrasting" learning scheme. However, we observe that unlike CL in computer vision domain,…

Machine Learning · Computer Science 2023-06-19 Wen-Zhi Li , Chang-Dong Wang , Hui Xiong , Jian-Huang Lai

Graph contrastive learning (GCL) emerges as the most representative approach for graph representation learning, which leverages the principle of maximizing mutual information (InfoMax) to learn node representations applied in downstream…

Machine Learning · Computer Science 2022-11-22 Yige Yuan , Bingbing Xu , Huawei Shen , Qi Cao , Keting Cen , Wen Zheng , Xueqi Cheng

Partial label (PL) learning tackles the problem where each training instance is associated with a set of candidate labels that include both the true label and irrelevant noise labels. In this paper, we propose a novel multi-level generative…

Machine Learning · Computer Science 2020-05-13 Yan Yan , Yuhong Guo

Hard negative mining has shown effective in enhancing self-supervised contrastive learning (CL) on diverse data types, including graph CL (GCL). The existing hardness-aware CL methods typically treat negative instances that are most similar…

Machine Learning · Computer Science 2024-01-09 Chaoxi Niu , Guansong Pang , Ling Chen

Link prediction tasks focus on predicting possible future connections. Most existing researches measure the likelihood of links by different similarity scores on node pairs and predict links between nodes. However, the similarity-based…

Machine Learning · Computer Science 2023-03-09 Zehua Zhang , Shilin Sun , Guixiang Ma , Caiming Zhong

knowledge graph-based recommendation methods have achieved great success in the field of recommender systems. However, over-reliance on high-quality knowledge graphs is a bottleneck for such methods. Specifically, the long-tailed…

Information Retrieval · Computer Science 2023-10-03 Yubo Gao , Haotian Wu

Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Huasong Zhong , Jianlong Wu , Chong Chen , Jianqiang Huang , Minghua Deng , Liqiang Nie , Zhouchen Lin , Xian-Sheng Hua

Graph Neural Networks (GNNs) are widely adopted in Web-related applications, serving as a core technique for learning from graph-structured data, such as text-attributed graphs. Yet in real-world scenarios, such graphs exhibit deficiencies…

Machine Learning · Computer Science 2025-10-03 Zhaoyan Wang , Zheng Gao , Arogya Kharel , In-Young Ko

Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot…

Machine Learning · Computer Science 2023-05-30 Chenyu Zheng , Guoqiang Wu , Chongxuan Li

Temporal Graph Learning, which aims to model the time-evolving nature of graphs, has gained increasing attention and achieved remarkable performance recently. However, in reality, graph structures are often incomplete and noisy, which…

Machine Learning · Computer Science 2023-08-16 Haozhen Zhang , Xueting Han , Xi Xiao , Jing Bai

This paper focuses on learning representation on the whole graph level in an unsupervised manner. Learning graph-level representation plays an important role in a variety of real-world issues such as molecule property prediction, protein…

Machine Learning · Computer Science 2024-01-08 Ge Wang , Zelin Zang , Jiangbin Zheng , Jun Xia , Stan Z. Li

While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensionality to learn informative and discriminative…

Neural and Evolutionary Computing · Computer Science 2024-02-20 Jintang Li , Huizhe Zhang , Ruofan Wu , Zulun Zhu , Baokun Wang , Changhua Meng , Zibin Zheng , Liang Chen

This work studies self-supervised graph learning for text-attributed graphs (TAGs) where nodes are represented by textual attributes. Unlike traditional graph contrastive methods that perturb the numerical feature space and alter the…

Machine Learning · Computer Science 2024-06-19 Yi Fang , Dongzhe Fan , Daochen Zha , Qiaoyu Tan

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Machine Learning · Computer Science 2017-08-22 Luke Taylor , Geoff Nitschke

Geodesic distances on manifolds have numerous applications in image processing, computer graphics and computer vision. In this work, we introduce an approach called `LGGD' (Learned Generalized Geodesic Distances). This method involves…

Machine Learning · Computer Science 2025-03-10 Amitoz Azad , Yuan Fang

Heterogeneous graph neural networks (HGNNs) have significantly propelled the information retrieval (IR) field. Still, the effectiveness of HGNNs heavily relies on high-quality labels, which are often expensive to acquire. This challenge has…

Machine Learning · Computer Science 2024-09-12 Siqing Li , Jin-Duk Park , Wei Huang , Xin Cao , Won-Yong Shin , Zhiqiang Xu
‹ Prev 1 8 9 10 Next ›