TSI-GNN: Extending Graph Neural Networks to Handle Missing Data in Temporal Settings.

TSI-GNN: Extending Graph Neural Networks to Handle Missing Data in Temporal Settings.
复制标题

DOI:
10.3389/fdata.2021.693869
复制
发表时间:
2021
影响因子:
3.1
通讯作者:
Bui AAT
Bui AAT
中科院分区:
其他
文献类型:
--
作者:
Gordon D;Petousis P;Zheng H;Zamanzadeh D;Bui AAT

文献摘要

参考文献

相似文献

我们提出了一种新的方法,通过扩展图表示学习将时间信息纳入二分图中的缺失数据。缺失的数据在几个领域都很丰富,特别是当观察是随着时间的推移进行的时候。大多数插补方法对数据的分布做出了强有力的假设。虽然新的方法可能会放松一些假设,但它们可能不考虑时间性。此外,当这些方法扩展到处理时间时,它们可能不会在没有重新训练的情况下推广。我们建议使用一个联合二分图的方法,将时间序列信息。具体而言,具有时间信息的观察节点和边用于消息传递以学习节点和边嵌入并通知插补任务。我们提出的方法,时间设置插补使用图神经网络(TSI-GNN),捕捉序列信息,然后可以使用在一个图神经网络的聚合函数。据我们所知,这是首次尝试使用联合二分图方法来捕获序列信息以处理缺失数据。我们使用几个基准数据集来测试我们的方法在各种条件下的性能,与经典和当代方法进行比较。我们进一步提供了管理生成的TSI-GNN模型的大小的见解。通过我们的分析,我们表明,将时间信息合并到二分图中可以提高30%和60%缺失率的表示,特别是在定期采样数据集中使用非线性模型进行下游预测任务时,并且在不同情况下与现有的时间方法相比具有竞争力。
We present a novel approach for imputing missing data that incorporates temporal information into bipartite graphs through an extension of graph representation learning. Missing data is abundant in several domains, particularly when observations are made over time. Most imputation methods make strong assumptions about the distribution of the data. While novel methods may relax some assumptions, they may not consider temporality. Moreover, when such methods are extended to handle time, they may not generalize without retraining. We propose using a joint bipartite graph approach to incorporate temporal sequence information. Specifically, the observation nodes and edges with temporal information are used in message passing to learn node and edge embeddings and to inform the imputation task. Our proposed method, temporal setting imputation using graph neural networks (TSI-GNN), captures sequence information that can then be used within an aggregation function of a graph neural network. To the best of our knowledge, this is the first effort to use a joint bipartite graph approach that captures sequence information to handle missing data. We use several benchmark datasets to test the performance of our method against a variety of conditions, comparing to both classic and contemporary methods. We further provide insight to manage the size of the generated TSI-GNN model. Through our analysis we show that incorporating temporal information into a bipartite graph improves the representation at the 30% and 60% missing rate, specifically when using a nonlinear model for downstream prediction tasks in regularly sampled datasets and is competitive with existing temporal methods under different scenarios.
DOI: 10.1038/s41586-020-2649-2
发表时间: 2020-09
期刊: Nature
影响因子: 64.8
作者:
Harris CR;Millman KJ;van der Walt SJ;Gommers R;Virtanen P;Cournapeau D;Wieser E;Taylor J;Berg S;Smith NJ;Kern R;Picus M;Hoyer S;van Kerkwijk MH;Brett M;Haldane A;Del Río JF;Wiebe M;Peterson P;Gérard-Marchant P;Sheppard K;Reddy T;Weckesser W;Abbasi H;Gohlke C;Oliphant TE
通讯作者: Oliphant TE
DOI: 10.1145/2939672.2939754
发表时间: 2016-08
期刊: KDD : proceedings. International Conference on Knowledge Discovery & Data Mining
影响因子: --
作者:
Grover A;Leskovec J
通讯作者: Leskovec J
DOI: 10.1214/ss/1177010269
发表时间: 1994-11-01
影响因子: 5.7
作者:
MENG, XL
通讯作者: MENG, XL
DOI: 10.1038/sdata.2016.35
发表时间: 2016-05-24
期刊: Scientific data
影响因子: 9.8
作者:
Johnson AE;Pollard TJ;Shen L;Lehman LW;Feng M;Ghassemi M;Moody B;Szolovits P;Celi LA;Mark RG
通讯作者: Mark RG
DOI: 10.1007/s10208-009-9045-5
发表时间: 2009-12-01
影响因子: 3
作者:
Candes, Emmanuel J.;Recht, Benjamin
通讯作者: Recht, Benjamin