GraphPL: 利用GNN实现Patchwork学习中高效且鲁棒的模态补全
GraphPL: Leveraging GNN for Efficient and Robust Modalities Imputation in Patchwork Learning
AI总结:
本文提出GraphPL,结合图神经网络与Patchwork学习,有效整合所有观测模态并保持噪声输入下的鲁棒性,在基准数据集和真实世界电子健康记录数据集上均取得SOTA性能。
摘要:
当前分布式多模态学习研究通常假设客户端可以访问所有模态的完整信息,这在实践中可能不成立。本文探讨了Patchwork学习,其中不同客户端可访问的模态不同,目标是无监督地为每个客户端补全缺失的模态。现有方法未能充分利用模态信息,因为它们倾向于仅依赖观测模态的一部分。为了解决这个问题,我们提出了GraphPL,结合图神经网络与Patchwork学习,灵活整合所有观测模态并保持在噪声输入下的鲁棒性。实验结果表明,GraphPL在基准数据集上实现了SOTA性能。在真实世界分布式电子健康记录数据集上的结果表明,GraphPL学习了强大的下游特征,并通过优越的模态补全能力实现了疾病预测等任务。
英文摘要:
Current research on distributed multi-modal learning typically assumes that clients can access complete information across all modalities, which may not hold in practice. In this paper, we explore patchwork learning, in which the modalities available to different clients vary, and the objective is to impute the missing modalities for each client in an unsupervised manner. Existing methods are shown not to fully utilize the modality information as they tend to rely on only a subset of the observed modalities. To address this issue, we propose GraphPL, which combines graph neural networks with patchwork learning to flexibly integrate all observed modalities and remains robust with noisy inputs. Experimental results show that GraphPL achieves SOTA performance on benchmark datasets. Our results on real-world distributed electronic health record dataset show GraphPL learns strong downstream features and enables tasks like disease prediction via superior modality imputation.
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。