Sequence Prediction Under Missing Data : An RNN Approach Without Imputation
원문 초록
Missing data scenarios are very common in ML applications in general and time-series/sequence applications are no exceptions. This paper pertains to a novel Recurrent Neural Network (RNN) based solution for sequence prediction under missing data. Our method is distinct from all existing approaches. It tries to encode the missingness patterns in the data directly without trying to impute data either before or during model building. Our encoding is lossless and achieves compression. It can be employed for both sequence classification and forecasting. We focus on forecasting here in a general context of multi-step prediction in presence of possible exogenous inputs. In particular, we propose novel variants of Encoder-Decoder (Seq2Seq) RNNs for this. The encoder here adopts the above mentioned pattern encoding, while at the decoder which has a different structure, multiple variants are feasible. We demonstrate the utility of our proposed architecture via multiple experiments on both single and multiple sequence (real) data-sets. We consider both scenarios where (i)data is naturally missing and (ii)data is synthetically masked.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Data Imputation for Multivariate Time Series Sensor Data with Large Gaps of Missing Data
DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection
Mind the gap: an experimental evaluation of imputation of missing values techniques in time series
SSIM -A Deep Learning Approach for Recovering Missing Time Series Sensor Data
A Review of the Long Horizon Forecasting Problem in Time Series Analysis
Cross-Domain Conditional Diffusion Models for Time Series Imputation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.