Computer Science > Machine Learning
[Submitted on 26 May 2024 (v1), last revised 26 Nov 2024 (this version, v2)]
Title:Unveiling the Secrets: How Masking Strategies Shape Time Series Imputation
View PDF HTML (experimental)Abstract:Time series imputation is a critical challenge in data mining, particularly in domains like healthcare and environmental monitoring, where missing data can compromise analytical outcomes. This study investigates the influence of diverse masking strategies, normalization timing, and missingness patterns on the performance of eleven state-of-the-art imputation models across three diverse datasets. Specifically, we evaluate the effects of pre-masking versus in-mini-batch masking, augmentation versus overlaying of artificial missingness, and pre-normalization versus post-normalization. Our findings reveal that masking strategies profoundly affect imputation accuracy, with dynamic masking providing robust augmentation benefits and overlay masking better simulating real-world missingness patterns. Sophisticated models, such as CSDI, exhibited sensitivity to preprocessing configurations, while simpler models like BRITS delivered consistent and efficient performance. We highlight the importance of aligning preprocessing pipelines and masking strategies with dataset characteristics to improve robustness under diverse conditions, including high missing rates. This study provides actionable insights for designing imputation pipelines and underscores the need for transparent and comprehensive experimental designs.
Submission history
From: Linglong Qian [view email][v1] Sun, 26 May 2024 18:05:12 UTC (98 KB)
[v2] Tue, 26 Nov 2024 13:26:58 UTC (268 KB)
Current browse context:
cs.LG
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
IArxiv Recommender
(What is IArxiv?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.