Back to Top

Paper Title

CAUSAL REPRESENTATION LEARNING FOR TEMPORAL EVENT FORECASTING IN HIGH-DIMENSIONAL SPARSE OBSERVATIONAL DATA QSETS

Authors

Keywords

  • Causal Representation Learning
  • Temporal Forecasting
  • High-dimensional Data
  • Sparse Sequences
  • Counterfactuals
  • Time-series Inference

Article Type

Research Article

Issue

Volume : 4 | Issue : 1 | Page No : 17-25

Published On

April, 2025

Downloads

Abstract

Forecasting temporal events from high-dimensional sparse observational data presents significant challenges due to noise, confounding factors, and data sparsity. Traditional sequence models often struggle in extracting underlying causal relationships, leading to biased forecasts. Causal Representation Learning (CRL) aims to uncover latent causal factors from observational data, thereby enabling more robust forecasting in complex temporal settings. This paper explores recent advancements in CRL for temporal event prediction, proposes an architecture integrating recurrent encoders with causal graph discovery, and evaluates performance on synthetic and real-world sparse datasets. Results show CRL-enhanced models significantly outperform standard LSTM baselines in both accuracy and counterfactual reasoning tasks.

View more >>

Uploded Document Preview