RIM: Reliable Influence-based Active Learning on Graphs

10/28/2021
by   Wentao Zhang, et al.
0

Message passing is the core of most graph models such as Graph Convolutional Network (GCN) and Label Propagation (LP), which usually require a large number of clean labeled data to smooth out the neighborhood over the graph. However, the labeling process can be tedious, costly, and error-prone in practice. In this paper, we propose to unify active learning (AL) and message passing towards minimizing labeling costs, e.g., making use of few and unreliable labels that can be obtained cheaply. We make two contributions towards that end. First, we open up a perspective by drawing a connection between AL enforcing message passing and social influence maximization, ensuring that the selected samples effectively improve the model performance. Second, we propose an extension to the influence model that incorporates an explicit quality factor to model label noise. In this way, we derive a fundamentally new AL selection criterion for GCN and LP–reliable influence maximization (RIM)–by considering quantity and quality of influence simultaneously. Empirical studies on public datasets show that RIM significantly outperforms current AL methods in terms of accuracy and efficiency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/08/2020

Masked Label Prediction: Unified Massage Passing Model for Semi-Supervised Classification

Graph convolutional network (GCN) and label propagation algorithms (LPA)...
research
03/02/2022

Information Gain Propagation: a new way to Graph Active Learning with Soft Labels

Graph Neural Networks (GNNs) have achieved great success in various task...
research
12/02/2020

Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning

Active learning is widely used to reduce labeling effort and training ti...
research
05/03/2021

Schema-Aware Deep Graph Convolutional Networks for Heterogeneous Graphs

Graph convolutional network (GCN) based approaches have achieved signifi...
research
10/28/2021

UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation

With the recent success of graph convolutional networks (GCNs), they hav...
research
01/30/2014

Joint Inference of Multiple Label Types in Large Networks

We tackle the problem of inferring node labels in a partially labeled gr...
research
10/14/2018

Personalized Embedding Propagation: Combining Neural Networks on Graphs with Personalized PageRank

Neural message passing algorithms for semi-supervised classification on ...

Please sign up or login with your details

Forgot password? Click here to reset