Dissimilar Nodes Improve Graph Active Learning

12/05/2022
by   Zhicheng Ren, et al.
0

Training labels for graph embedding algorithms could be costly to obtain in many practical scenarios. Active learning (AL) algorithms are very helpful to obtain the most useful labels for training while keeping the total number of label queries under a certain budget. The existing Active Graph Embedding framework proposes to use centrality score, density score, and entropy score to evaluate the value of unlabeled nodes, and it has been shown to be capable of bringing some improvement to the node classification tasks of Graph Convolutional Networks. However, when evaluating the importance of unlabeled nodes, it fails to consider the influence of existing labeled nodes on the value of unlabeled nodes. In other words, given the same unlabeled node, the computed informative score is always the same and is agnostic to the labeled node set. With the aim to address this limitation, in this work, we introduce 3 dissimilarity-based information scores for active learning: feature dissimilarity score (FDS), structure dissimilarity score (SDS), and embedding dissimilarity score (EDS). We find out that those three scores are able to take the influence of the labeled set on the value of unlabeled candidates into consideration, boosting our AL performance. According to experiments, our newly proposed scores boost the classification accuracy by 2.1 capable of generalizing to different Graph Neural Network architectures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/05/2015

Learning in Unlabeled Networks - An Active Learning and Inference Approach

The task of determining labels of all network nodes based on the knowled...
research
08/20/2021

Influence Selection for Active Learning

The existing active learning methods select the samples by evaluating th...
research
07/31/2023

DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification

Node classification is one of the core tasks on attributed graphs, but s...
research
12/02/2022

SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction

Graph neural networks have achieved significant success in representatio...
research
07/09/2020

Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generation

Node classification in attributed graphs is an important task in multipl...
research
08/17/2023

Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning

Graph Active Learning (GAL), which aims to find the most informative nod...
research
09/15/2011

Active Learning for Node Classification in Assortative and Disassortative Networks

In many real-world networks, nodes have class labels, attributes, or var...

Please sign up or login with your details

Forgot password? Click here to reset