Zobrazeno 1 - 10
of 117
pro vyhledávání: '"Zhang, Shengzhong"'
Graph recommender (GR) is a type of graph neural network (GNNs) encoder that is customized for extracting information from the user-item interaction graph. Due to its strong performance on the recommendation task, GR has gained significant attention
Externí odkaz:
http://arxiv.org/abs/2407.17723
In this work, we discover a phenomenon of community bias amplification in graph representation learning, which refers to the exacerbation of performance bias between different classes by graph representation learning. We conduct an in-depth theoretic
Externí odkaz:
http://arxiv.org/abs/2312.04883
Graph contrastive learning (GCL) has become a powerful tool for learning graph data, but its scalability remains a significant challenge. In this work, we propose a simple yet effective training framework called Structural Compression (StructComp) to
Externí odkaz:
http://arxiv.org/abs/2312.04865
Publikováno v:
Thirty-seventh Conference on Neural Information Processing Systems. (NeurIPS 2023)
This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data. Our approach integrates imbalanced node classification and Bias-Variance Decomposition, establishing a
Externí odkaz:
http://arxiv.org/abs/2310.18765
Extremely skewed label distributions are common in real-world node classification tasks. If not dealt with appropriately, it significantly hurts the performance of GNNs in minority classes. Due to its practical importance, there have been a series of
Externí odkaz:
http://arxiv.org/abs/2303.10371
Given the ubiquitous existence of graph-structured data, learning the representations of nodes for the downstream tasks ranging from node classification, link prediction to graph classification is of crucial importance. Regarding missing link inferen
Externí odkaz:
http://arxiv.org/abs/2204.09508
Autor:
Fan, Dequan, Qiao, Kai, Zhang, Shengzhong, Chen, Xiaofang, Wang, Hongtao, Zhang, Ying, Zhang, Yanpeng, Yang, Yang, Hu, Fangzhou, Wang, Yangfeng, Chen, Zihua, Liang, Feng, Zhai, Dong, Kumar Marella, Ravi, Yu, Tie
Publikováno v:
In Separation and Purification Technology 20 September 2024 344
Scalability of graph neural networks remains one of the major challenges in graph machine learning. Since the representation of a node is computed by recursively aggregating and transforming representation vectors of its neighboring nodes from previo
Externí odkaz:
http://arxiv.org/abs/2106.05150
Large-scale network embedding is to learn a latent representation for each node in an unsupervised manner, which captures inherent properties and structural information of the underlying graph. In this field, many popular approaches are influenced by
Externí odkaz:
http://arxiv.org/abs/2006.16499
Publikováno v:
Zhou, Z., Shi, J., Zhang, S., Huang, Z., & Li, Q. (2023). Effective Stabilized Self-Training on Few-Labeled Graph Data. Information Sciences
Graph neural networks (GNNs) are designed for semi-supervised node classification on graphs where only a subset of nodes have class labels. However, under extreme cases when very few labels are available (e.g., 1 labeled node per class), GNNs suffer
Externí odkaz:
http://arxiv.org/abs/1910.02684