[74] J. Zeng and P. Xie, “Contrastive self-supervised learning for graph classification,” in AAAI, vol. 35, no. 12, 2021. [75] S. Suresh, P. Li, C. Hao, and J. Neville, “Adversarial graph aug- mentation to improve graph contrastive learning,” in NeurIPS, 2021. [76] J. K...
在 NeurIPS 2021 的论文 Adversarial Graph Augmentation to Improve Graph Contrastive Learning 中,作者从数据增强如何保留图的信息出发,假设增强出的两个 View 之间并不是互信息越大越好,因为这些互信息中可能包含大量噪音。 作者引入信息瓶颈 (Information Bottleneck)原则,认为更好的 View 应该是在共同保留图本身的特...
SLAPS: Self-Supervision Improves Structure Learning for Graph Neural NetworksBahare Fatemi (University of British Columbia) · Layla El Asri (Universite de Lorraine) · Seyed Mehran Kazemi (University of British Columbia) Graph Adversarial Self-Supervised LearningLongqi Yang (National University of Defense...
2、Adversarial attack and defense on graph data: A survey. arXiv , 2018. 3、Graph sanitation with application to node classification. arXiv preprint arXiv 2021. 4、On the unreasonable effectiveness of feature propagation in learning on graphs with missing node features. arXiv, 2021. ...
generative-adversarial-network gan data-generation multiplex graph-generation gender-classification connectome brain-connectivity brain-network graph-embedding predictive-learning geometric-deep-learning brain-networks predictive-intelligence morphological-brain-multiplexes brain-graph-translation predicting-brain-multiple...
To improve the robustness of graph representation learning, we propose a novel Graph Adversarial Contrastive Learning framework (GraphACL) by introducing adversarial augmentations into graph self-supervised learning. In this framework, we maximize the mutual information between local and global ...
adversarial-learningevidence-basedfake-news-detectiongraph-contrastive-learningsemantic-learning UpdatedApr 23, 2024 Python kunzhan/M-ILBO Star18 Code Issues Pull requests ACM MM 2023 (Oral): Entropy neural estimation for graph contrastive learning ...
[ICDM 2019] Domain-Adversarial Graph Neural Networks for Text Classification [paper] Graph Self-supervised Learning [arXiv 2022] GraphTTA: Test Time Adaptation on Graph Neural Networks [paper] [WWW 2022] Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift [paper]...
Learning Robust Representation through Graph Adversarial Contrastive Learning To improve the robustness of graph representation learning, we propose a novel Graph Adversarial Contrastive Learning framework (GraphACL) by introducing adversarial augmentations into graph self-supervised learning. In this framework,...
GPS: Graph Contrastive Learning via Multi-scale Augmented Views from Adversarial Pooling 29 Jan 2024 · Wei Ju, Yiyang Gu, Zhengyang Mao, Ziyue Qiao, Yifang Qin, Xiao Luo, Hui Xiong, Ming Zhang · Edit social preview Self-supervised graph representation learning has recently shown considerable ...