Meta-Active Learning for Node Response Prediction in Graphs
원문 초록
Meta-learning is an important approach to improve machine learning performance with a limited number of observations for target tasks. However, when observations are unbalancedly obtained, it is difficult to improve the performance even with meta-learning methods. In this paper, we propose an active learning method for meta-learning on node response prediction tasks in attributed graphs, where nodes to observe are selected to improve performance with as few observed nodes as possible. With the proposed method, we use models based on graph convolutional neural networks for both predicting node responses and selecting nodes, by which we can predict responses and select nodes even for graphs with unseen response variables. The response prediction model is trained by minimizing the expected test error. The node selection model is trained by maximizing the expected error reduction with reinforcement learning. We demonstrate the effectiveness of the proposed method with 11 types of road congestion prediction tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MetaSTNet: Multimodal Meta-learning for Cellular Traffic Conformal Prediction
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
Cautious Next Token Prediction
Where, What, Why: Towards Explainable Driver Attention Prediction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.