Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning
Open Access
- 21 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4380-4384
Abstract
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.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Graph Pointer Neural NetworksProceedings of the AAAI Conference on Artificial Intelligence, 2022
- HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization2022
- Non-Local Graph Neural NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Scaling Up Graph Neural Networks Via Graph Coarsening2021
- Intention-aware Heterogeneous Graph Attention Networks for Fraud Transactions Detection2021
- ALG: Fast and Accurate Active Learning Framework for Graph Convolutional Networks2021
- Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection2021
- Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
- Active Discriminative Text Representation LearningProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Maximizing the spread of influence through a social network2003