Research map / Label-efficient and robust learning / Recognition and long-tail
TaGiTeD: Predictive Task Guided Tensor Decomposition for Representation Learning from Electronic Health Records
Kai Yang, Xiang Li, Haifeng Liu, Jing Mei, Guotong Xie, Junfeng Zhao, Bing Xie, Fei Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add supervised task-guided penalty (log-loss) to Poisson tensor decomposition | CP-APR with Logistic Regression · Small dense EHR hospitalization | AUC: 0.7593 -> 0.7886 | Improved |
| add supervised task-guided penalty (log-loss) to Poisson tensor decomposition | CP-APR with Random Forest · Small dense EHR hospitalization | AUC: 0.7435 -> 0.7627 | Improved |
| use hinge-loss penalty instead of none (SVM classifier) | CP-APR with SVM · Small dense EHR hospitalization | AUC: 0.7488 -> 0.7877 | Improved |
| add supervised penalty to tensor decomposition | CP-APR with Logistic Regression · Big sparse EHR hospitalization | AUC: 0.6325 -> 0.653 | Improved |
| add supervised penalty to tensor decomposition | CP-APR with Random Forest · Big sparse EHR hospitalization | AUC: 0.6529 -> 0.655 (Hinge), 0.6465 (Log) | Mixed |
| add supervised quadratic-loss penalty | CP-APR · Small dense EHR expense regression | R2: 0.2653 -> 0.2830 | Improved |
| add supervised quadratic-loss penalty | CP-APR · Small dense EHR expense regression | RMSE: 10.750 -> 7.79 | Improved |
| replace vector-based PCA with tensor decomposition (CP-APR) | Logistic Regression classifier · Small dense EHR hospitalization | AUC: 0.7190 -> 0.7593 | Improved |
Closest papers by meaning
- One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models (NeurIPS 2026 · similarity 0.84)
- Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records (NeurIPS 2024 · similarity 0.83)
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.83)
- SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction (NeurIPS 2024 · similarity 0.83)
- MOTOR: A Time-to-Event Foundation Model For Structured Medical Records (ICLR 2024 · similarity 0.83)
- Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data (ICLR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
