Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning

by   Tianmeng Yang, et al.
HUAWEI Technologies Co., Ltd.
Peking University

Graph Active Learning (GAL), which aims to find the most informative nodes in graphs for annotation to maximize the Graph Neural Networks (GNNs) performance, has attracted many research efforts but remains non-trivial challenges. One major challenge is that existing GAL strategies may introduce semantic confusion to the selected training set, particularly when graphs are noisy. Specifically, most existing methods assume all aggregating features to be helpful, ignoring the semantically negative effect between inter-class edges under the message-passing mechanism. In this work, we present Semantic-aware Active learning framework for Graphs (SAG) to mitigate the semantic confusion problem. Pairwise similarities and dissimilarities of nodes with semantic features are introduced to jointly evaluate the node influence. A new prototype-based criterion and query policy are also designed to maintain diversity and class balance of the selected nodes, respectively. Extensive experiments on the public benchmark graphs and a real-world financial dataset demonstrate that SAG significantly improves node classification performances and consistently outperforms previous methods. Moreover, comprehensive analysis and ablation study also verify the effectiveness of the proposed framework.


Label-Wise Message Passing Graph Neural Network on Heterophilic Graphs

Graph Neural Networks (GNNs) have achieved remarkable performance in mod...

Partition-Based Active Learning for Graph Neural Networks

We study the problem of semi-supervised learning with Graph Neural Netwo...

Deep Active Graph Representation Learning

Graph neural networks (GNNs) aim to learn graph representations that pre...

Graph Policy Network for Transferable Active Learning on Graphs

Graph neural networks (GNNs) have been attracting increasing popularity ...

Towards Open Temporal Graph Neural Networks

Graph neural networks (GNNs) for temporal graphs have recently attracted...

Dissimilar Nodes Improve Graph Active Learning

Training labels for graph embedding algorithms could be costly to obtain...

Clarify Confused Nodes Through Separated Learning

Graph neural networks (GNNs) have achieved remarkable advances in graph-...

Please sign up or login with your details

Forgot password? Click here to reset