AI 中文总结
MTLiquid通过共享骨干网络、多输入输出头及损失加权和比例数据训练策略，在连续时间医疗监测中实现高效多任务学习，性能与单任务相当，内存成本降低44%-94%。
AI 中文摘要
连续时间感知与监测以及及时准确的决策对于许多现实世界应用至关重要。在医疗监测系统中，生理信号通常以不规律的时间间隔可用或采样，因此需要连续时间处理以提供准确的预测。此外，此类系统通常需要解决多个检测/预测任务，以从不同生理方面提供全面的患者评估，从而实现更准确的决策。为解决这一问题，可以采用连续时间神经网络（CTNNs）。然而，现有最先进的工作通常在每个网络中仅解决单一任务，从而限制了其效率提升。为解决这一局限，我们提出了MTLiquid，一种新颖的方法论，通过有效的网络设计和训练策略，在医疗监测系统的连续时间处理中实现高效的多任务学习。MTLiquid采用：（1）多个输入和输出头以适应不同任务，同时在任务间共享同一骨干网络；以及（2）一种有效的训练策略，利用损失加权技术平衡不同任务间的学习更新，并采用比例数据呈现技术来解决数据集规模不均衡的问题。针对ICU患者死亡预测（P12）和脓毒症早期检测（P19）任务的实验结果表明，MTLiquid取得了强劲的性能（P12的AUROC为0.84，P19的AUROC为0.94），与连续时间网络（P12的AUROC为0.84，P19的AUROC为0.95）和离散时间网络（P12的AUROC为0.79-0.82，P19的AUROC为0.92-0.94）中最先进的单任务学习相当，同时内存成本显著降低44%-94%。这些结果凸显了我们的MTLiquid方法论在实现轻量级连续时间医疗监测系统以促进更好决策方面的潜力。
英文摘要
Continuous-time sensing and monitoring with timely and accurate decision-making are critical for many real-world applications. In healthcare monitoring systems, physiological signals are often available or sampled at irregular time intervals, hence requiring continuous-time processing to provide accurate prediction. Moreover, such systems often need to solve multiple detection/prediction tasks to provide a comprehensive patient review from different physiological aspects for more accurate decision-making. To solve this, continuous-time neural networks (CTNNs) can be employed. However, state-of-the-art works typically solve only one task at each network, thereby limiting their efficiency gains. To address this limitation, we propose MTLiquid, a novel methodology to enable efficient multi-task learning in continuous-time processing for healthcare monitoring systems through effective network design and training strategy. MTLiquid employs: (1) multiple input and output heads to accommodate different tasks, while sharing the same backbone network across tasks; as well as (2) an effective training strategy that leverages a loss-weighting technique to balance learning updates across different tasks and a proportional data presentation technique to address imbalanced dataset sizes. Experimental results for mortality prediction (P12) and sepsis early detection (P19) tasks for ICU patients show that, MTLiquid achieves strong performance (AUROC: 0.84 for P12 and 0.94 for P19) comparable to the state-of-the-art single-task learning in both continuous-time networks (AUROC: 0.84 for P12 and 0.95 for P19) and discrete-time networks (AUROC: 0.79-0.82 for P12 and 0.92-0.94 for P19), while incurring significantly smaller memory cost by 44%-94%. These results highlight the potential of our MTLiquid methodology to enable lightweight continuous-time healthcare monitoring systems for better decision-making.
Comments8 pages, 1 figure, 2 tables
