Information science Graph-based learning for information systems THE UNIVERSITY OF ARIZONA Hsinchun Chen LiXinThe advance of information technologies (IT) makes it possible to collect a massive amount of data in business applications and information systems. The increasing data volumes require more ...
遵循SSL的框架,GSSL方法的损失函数也可以推广到SSL的损失函数中,其中包含三个部分,如Eq. (1) \mathcal{L}(f)=\underbrace{\mathcal{L}_s\left(f, \mathcal{D}_l\right)}_{\text {supervised loss }}+\lambda \underbrace{\mathcal{L}_u\left(f, \mathcal{D}_u\right)}_{\text {unsupervised...
[Active Learning] & [Imbalanced Data] 主动学习在标注开销的任务场景中交互式地选择高信息量地无标记样本进行标注和模型训练。这篇文章关注到现实世界中极端不平衡的数据场景。例如,医疗样本中的病例往往较少,欺诈识别中的欺诈样本往往较少,而它们的数据标注要需要花费专家大量的精力。
因此,POI 之间的距离影响可能包含多种因素,仅仅基于距离的表示并不合理。 为了解决上面这些问题,论文专注于对 POI 进行更好地表征,提出了一个新的 Disentangled Representation-enhanced Attention Network (DRAN),将 POI 表示分解为多个独立的分量;提出了 Disentangled Graph Convolution Network (DGCN) 学习 POI 表征,...
Current recommendation systems often struggle to incorporate high-dimensional visual data into graph-based learning models effectively. This limitation presents a substantial opportunity to enhance the precision and effectiveness of fashion recommendations. In this paper, we present the Visual-aware Graph ...
Many point cloud processing models based on deep learning have been proposed by researchers recently. However, they are all large﹕ample dependent, which means that a large amount of manually labelled training data are needed to train the model, resulting in huge labor cost. In this paper, to...
links to conference publications in graph-based deep learning - naganandy/graph-based-deep-learning-literature
Transfer learning is the task of leveraging the information from labeled examples in some domains to predict the labels for examples in another domain. It finds abundant practical a
Learning to read with GraphoLearn is fun and easy, so that the child is able to play it alone. It is like an additional teacher who helps children to learn important letter sounds correspondences, which are the building blocks of reading skill. ...
2.1 Graph-based Learning 在属性图上,最流行的任务之一是节点分类,旨在通过考虑节点特征和图结构来预测图中节点的标签。 现有的节点分类工作主要分为两大类:图拉普拉斯正则化和基于图嵌入的方法。基于图嵌入的方法学习编码图数据的节点嵌入,现在许多模型都是使用的这种方法。 利用深度神经网络(基于神经图的学习方法)方...