Active Learning for Node Classification: An Evaluation

Abstract

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.

An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification

“…With the help of domain experts, the tedious process of manual identification and grouping of microorganisms was simplified. In the absence of a domain specialist, this work would have required additional resources and a new stack of algorithms such as active learning [ 77 ] and deep learning [ 78 ].…”

Deep learning model construction for a semi-supervised classification with feature learning

“…It uses an edge sampling technique to take advantage of social graph features by studying each actor's history concerning nearby nodes to create vector-space embeddings for each actor. Madhawa et al [23] looked at using an adaptive learning algorithm to increase node classification performance on attributed graph labels. Li et al [43] present a novel semi-supervised learning technique combining dynamic graph learning and selfpaced learning.…”

CoarSAS2hvec: Heterogeneous Information Network Embedding with Balanced Network Sampling

“…We consider nine embedding methods as the baseline, including two GNN-based and seven structure-preserving state-of-the-arts. CoarSAS2hvec outperforms the baseline methods in node classification [ 23 ] and community detection [ 24 ] using four real-world data sets. The ablation study demonstrates that the samples collected by CoarSAS contain a higher information entropy than other methods, hence capturing more diverse information of HIN.…”