Active Discriminative Network Representation Learning

Gao, Li; Yang, Hong; Zhou, Chuan; Wu, Jia; Pan, Shirui; Hu, Yue

doi:10.24963/ijcai.2018/296

Cited by 58 publications

(55 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Labels are chosen from informative nodes with the help of an oracle for training GNNs. Cai et al [18], Gao et al [49], Hu et al [64] show that the labeling efficiency can be substantially increased by choosing high-degree nodes and uncertain nodes (informative nodes).…”

Section: Theoretical Aspectmentioning

confidence: 99%

Graph Neural Networks: Methods, Applications, and Opportunities

Waikhom,

Patgiri

2021

Preprint

View full text Add to dashboard Cite

In the last decade or so, we have witnessed deep learning reinvigorating the machine learning field. It has solved many problems in the domains of computer vision, speech recognition, natural language processing, and various other tasks with state-of-the-art performance. The data is generally represented in the Euclidean space in these domains. Various other domains conform to non-Euclidean space, for which graph is an ideal representation. Graphs are suitable for representing the dependencies and interrelationships between various entities. Traditionally, handcrafted features for graphs are incapable of providing the necessary inference for various tasks from this complex data representation. Recently, there is an emergence of employing various advances in deep learning to graph data-based tasks. This article provides a comprehensive survey of graph neural networks (GNNs) in each learning setting: supervised, unsupervised, semi-supervised, and self-supervised learning. Taxonomy of each graph based learning setting is provided with logical divisions of methods falling in the given learning setting. The approaches for each learning task are analyzed from both theoretical as well as empirical standpoints. Further, we provide general architecture guidelines for building GNNs. Various applications and benchmark datasets are also provided, along with open challenges still plaguing the general applicability of GNNs.

show abstract

Section: Theoretical Aspectmentioning

confidence: 99%

Graph Neural Networks: Methods, Applications, and Opportunities

Waikhom,

Patgiri

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…While the above methods concentrate on supervised learning, AGE [3] and ANRMAB [15] are proposed for active learning on semi-supervised scenarios (e.g., graph) by using both the node features and graph structure. Recently, clustering-based active learning methods have been proposed for GNNs, such as Featprop [61] and LSCALE [38].…”

Section: Data Selection Problemsmentioning

confidence: 99%

“…Baselines. We compare Grain (ball-D) and Grain (NN-D) with the following baselines: Random, Degree, AGE [3], ANRMAB [15], K-Center-Greedy (KCG) [46]. A detailed introduction of these baseline methods can be found in Appendix A.5.…”

Section: Experiments 41 Experimental Settingsmentioning

confidence: 99%

Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization

Zhang,

Yang,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets. However, recent deep learning models have moved forward from independent and identically distributed data to graph-structured data, such as social networks, ecommerce user-item graphs, and knowledge graphs. This evolution has led to the emergence of Graph Neural Networks (GNNs) that go beyond the models existing data selection methods are designed for. Therefore, we present Grain, an efficient framework that opens up a new perspective through connecting data selection in GNNs with social influence maximization. By exploiting the common patterns of GNNs, Grain introduces a novel feature propagation concept, a diversified influence maximization objective with novel influence and diversity functions, and a greedy algorithm with an approximation guarantee into a unified framework. Empirical studies on public datasets demonstrate that Grain significantly improves both the performance and efficiency of data selection (including active learning and core-set selection) for GNNs. To the best of our knowledge, this is the first attempt to bridge two largely parallel threads of research, data selection, and social influence maximization, in the setting of GNNs, paving new ways for improving data efficiency.

show abstract

“…Therefore, selecting query nodes uniformly in random coupled with a recent GNN model can easily outperform such AL models. AL models which utilize recent GNN architectures [ 41 , 42 ] are limited. Moreover, a comprehensive comparison of AL algorithms proposed for other domains of data has not been done yet.…”

Section: Active Learning For Graph Classification Problemsmentioning

confidence: 99%

Active Learning for Node Classification: An Evaluation

Madhawa

Murata

2020

Entropy

View full text Add to dashboard Cite

Current breakthroughs in the field of machine learning are fueled by the deployment of deep neural network models. Deep neural networks models are notorious for their dependence on large amounts of labeled data for training them. Active learning is being used as a solution to train classification models with less labeled instances by selecting only the most informative instances for labeling. This is especially important when the labeled data are scarce or the labeling process is expensive. In this paper, we study the application of active learning on attributed graphs. In this setting, the data instances are represented as nodes of an attributed graph. Graph neural networks achieve the current state-of-the-art classification performance on attributed graphs. The performance of graph neural networks relies on the careful tuning of their hyperparameters, usually performed using a validation set, an additional set of labeled instances. In label scarce problems, it is realistic to use all labeled instances for training the model. In this setting, we perform a fair comparison of the existing active learning algorithms proposed for graph neural networks as well as other data types such as images and text. With empirical results, we demonstrate that state-of-the-art active learning algorithms designed for other data types do not perform well on graph-structured data. We study the problem within the framework of the exploration-vs.-exploitation trade-off and propose a new count-based exploration term. With empirical evidence on multiple benchmark graphs, we highlight the importance of complementing uncertainty-based active learning models with an exploration term.

show abstract

Active Discriminative Network Representation Learning

Cited by 58 publications

References 18 publications

Graph Neural Networks: Methods, Applications, and Opportunities

Graph Neural Networks: Methods, Applications, and Opportunities

Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization

Active Learning for Node Classification: An Evaluation

Contact Info

Product

Resources

About