arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08765cs.LG
收藏

基于图神经网络的自适应迁移学习

Adaptive Transfer Learning on Graph Neural Networks

Microsoft Research Asia(微软亚洲研究院);Beihang University(北京航空航天大学);University of Maryland, College Park(马里兰大学帕克分校)

Xueting Han, Zhenhuan Huang, Bang An, Jing Bai

摘要:

图神经网络(GNN)被广泛用于学习图结构数据的强大表示。最近的工作表明,将知识从自我监督任务转移到下游任务可以进一步改进图形表示。然而,在优化目标和训练数据方面,自监督任务和下游任务之间存在固有的差距。传统的预培训方法可能是不够有效的知识转移,因为他们没有做任何适应下游的任务。为了解决这些问题,我们提出了一个新的迁移学习范式的GNNs,可以有效地利用自我监督任务作为辅助任务,以帮助目标任务。我们的方法将自适应地选择和组合不同的辅助任务与目标任务的微调阶段。我们设计了一个自适应的辅助损失加权模型,通过量化辅助任务和目标任务之间的一致性来学习辅助任务的权重。此外,我们通过元学习来学习加权模型。我们的方法可以应用于各种迁移学习方法,它不仅在多任务学习中表现良好,而且在预训练和微调。对多个下游任务的综合实验表明,所提方法能有效地将辅助任务与目标任务相结合,与现有方法相比,性能有显著提高。

英文摘要:

Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further improve graph representation. However, there is an inherent gap between self-supervised tasks and downstream tasks in terms of optimization objective and training data. Conventional pre-training methods may be not effective enough on knowledge transfer since they do not make any adaptation for downstream tasks. To solve such problems, we propose a new transfer learning paradigm on GNNs which could effectively leverage self-supervised tasks as auxiliary tasks to help the target task. Our methods would adaptively select and combine different auxiliary tasks with the target task in the fine-tuning stage. We design an adaptive auxiliary loss weighting model to learn the weights of auxiliary tasks by quantifying the consistency between auxiliary tasks and the target task. In addition, we learn the weighting model through meta-learning. Our methods can be applied to various transfer learning approaches, it performs well not only in multi-task learning but also in pre-training and fine-tuning. Comprehensive experiments on multiple downstream tasks demonstrate that the proposed methods can effectively combine auxiliary tasks with the target task and significantly improve the performance compared to state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑