arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.05883cs.LGcs.AIstat.ML
收藏

NeuralPrefix:一种零样本传感数据插补插件

NeuralPrefix: A Zero-shot Sensory Data Imputation Plugin

Data61 CSIRO(澳大利亚联邦科学与工业研究组织Data61)

Abdelwahed Khamis, Sara Khalifa

AI总结:

针对传感数据间歇性问题,提出零样本插补框架NeuralPrefix,作为任务模型前的生成式神经组件,通过连续动力系统和ODE估计状态,在多数据集上实现50%缺失率下0.93-0.96的SSIM,且零样本泛化至新模态。

摘要:

现实世界中的传感挑战(如传感器故障、通信问题和功率限制)会导致数据间歇性,这一问题会破坏假设连续数据流的传统分类任务。以往的研究通过设计定制化解决方案(即特定任务和/或特定模态的插补)来解决该问题。这些方法虽然对其预期目的有效,但在不同任务和传感器模态间的适用性有限。这引发了一个重要问题:我们能否构建一个与任务无关的插补流水线,无需额外训练即可迁移到新传感器?在这项工作中,我们形式化了零样本插补的概念,并提出一种新方法,使预训练模型能够适应处理数据间歇性。该框架名为NeuralPrefix,是一种生成式神经组件,在推理期间位于任务模型之前,填补数据间歇性造成的空白。NeuralPrefix构建为连续动力系统,其内部状态可通过求解常微分方程(ODE)在任意时间点估计。这种方法实现了更通用、适应性更强的插补方法,克服了特定任务和特定模态解决方案的局限性。我们在多个传感数据集上对NeuralPrefix进行了全面评估,证明其在不同领域的有效性。在缺失率高达50%的间歇性数据上测试时,NeuralPrefix准确恢复了所有缺失样本,SSIM得分在0.93-0.96之间。零样本评估表明,即使测量来自不同模态,NeuralPrefix也能很好地泛化到未见过的数据集。

英文摘要:

Real-world sensing challenges such as sensor failures, communication issues, and power constraints lead to data intermittency. An issue that is known to undermine the traditional classification task that assumes a continuous data stream. Previous works addressed this issue by designing bespoke solutions (i.e. task-specific and/or modality-specific imputation). These approaches, while effective for their intended purposes, had limitations in their applicability across different tasks and sensor modalities. This raises an important question: Can we build a task-agnostic imputation pipeline that is transferable to new sensors without requiring additional training? In this work, we formalise the concept of zero-shot imputation and propose a novel approach that enables the adaptation of pre-trained models to handle data intermittency. This framework, named NeuralPrefix, is a generative neural component that precedes a task model during inference, filling in gaps caused by data intermittency. NeuralPrefix is built as a continuous dynamical system, where its internal state can be estimated at any point in time by solving an Ordinary Differential Equation (ODE). This approach allows for a more versatile and adaptable imputation method, overcoming the limitations of task-specific and modality-specific solutions. We conduct a comprehensive evaluation of NeuralPrefix on multiple sensory datasets, demonstrating its effectiveness across various domains. When tested on intermittent data with a high 50% missing data rate, NeuralPreifx accurately recovers all the missing samples, achieving SSIM score between 0.93-0.96. Zero-shot evaluations show that NeuralPrefix generalises well to unseen datasets, even when the measurements come from a different modality.

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。

↑