Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels
Abstract
Traditional supervised learning heavily relies on human-annotated datasets, especially in data-hungry neural approaches. However, various tasks, especially multi-label tasks like document-level relation extraction, pose challenges in fully manual annotation due to the specific domain knowledge and large class sets. Therefore, we address the multi-label positive-unlabelled learning (MLPUL) problem, where only a subset of positive classes is annotated. We propose Mixture Learner for Partially Annotated Classification (MLPAC), an RL-based framework combining the exploration ability of reinforcement learning and the exploitation ability of supervised learning. Experimental results across various tasks, including document-level relation extraction, multi-label image classification, and binary PU learning, demonstrate the generalization and effectiveness of our framework.
Cite
@article{arxiv.2406.16293,
title = {Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels},
author = {Zixia Jia and Junpeng Li and Shichuan Zhang and Anji Liu and Zilong Zheng},
journal= {arXiv preprint arXiv:2406.16293},
year = {2024}
}