본문
제품 정보
Domain Adaptation for Regression under Monotonic Causal Shift
| Date | 2024.01.11. |
|---|---|
| Speaker | 부도현 |
- 이전글Causality Inspired Representation Learning for Domain Generalization 24.02.15
- 다음글Heterogeneous Matrix Factorization: When Features Differ by Datasets 24.01.16
Topic
- Domain Adaptation under monotonic causal shift via Surrogate Domain Estimation (DASDE)
- Domain Adaptation under monotonic causal shift via Causal Distribution Transformation (DACDT)
Keywords
- Monotonic Causal Shift
- Regression for Tabular Dataset
- Data Augmentation
- Multi-Domain Adaptation
- Restore Function Estimation
Reference
- Runje, Davor, and Sharath M. Shankaranarayana. "Constrained monotonic neural networks." International Conference on Machine Learning. PMLR, 2023.
- Clevert, Djork-Arné, Thomas Unterthiner, and Sepp Hochreiter. "Fast and accurate deep network learning by exponential linear units (elus)." arXiv preprint arXiv:1511.07289 (2015).
- Taghiyarrenani, Zahra, et al. "Multi-domain adaptation for regression under conditional distribution shift." Expert Systems with Applications 224 (2023): 119907.
- Finn, Chelsea, Pieter Abbeel, and Sergey Levine. "Model-agnostic meta-learning for fast adaptation of deep networks." International conference on machine learning. PMLR, 2017.
- Finn, Chelsea, et al. "Online meta-learning." International Conference on Machine Learning. PMLR, 2019.
[이 게시물은 관리자님에 의해 2024-02-26 13:30:56 Seminar에서 이동 됨]
[이 게시물은 관리자님에 의해 2024-02-26 13:31:06 Seminar에서 이동 됨]
첨부파일
-
Domain Adaptation for Regression under Monotonic Causal Shift.pdf (1.2M)
24회 다운로드 | DATE : 2024-01-15 18:24:18
저작자표시-비영리-동일조건변경허락(BY-NC-SA)
저작자와 출처 등을 표시하면 저작물의 변경, 2차적 저작물의 작성을 포함한 자유이용을 허락합니다. 단 영리적 이용은 허용되지 않고 2차적 저작물에는 원저작물에 적용된 라이선스와 동일한 라이선스를 적용해야 합니다.