Temporally and Distributionally Robust Optimization for Cold-start Recommendation (AAAI'24)
-
Updated
Mar 28, 2024 - Python
Temporally and Distributionally Robust Optimization for Cold-start Recommendation (AAAI'24)
A curated list of Distribution Shift papers/articles and recent advancements.
Resources for the paper titled "Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts". Accepted at NeurIPS 2022.
Robust and Highly Sensitive Covariate Shift Detection using XGBoost
Code for the Conditional Mutual Information-Debiasing (CMID) method.
Code for "Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning"
Implementation of paper: Equivariant Learning for Out-of-Distribution Cold-start Recommendation. (backbone model CLCRec) (MM'23)
Implementation codes for NeurIPS23 paper "Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts"
Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"
Code for "Improving Stain Invariance of CNNs for Segmentation by Fusing Channel Attention and Domain-Adversarial Training"
CLIFT : Analysing Natural Distribution Shift on Question Answering Models in Clinical Domain
Coping with Label Shift via Distributionally Robust Optimisation
"RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning" by Yue Duan (ECCV 2022)
Code accompanying our paper titled Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms
Gated Domain Units (GDU) aim to make your deep learning models robust against distribution shifts when applied in the real-world.
A Python Library for Biquality Learning
[ICLR 2023] Official Tensorflow implementation of "Distributionally Robust Post-hoc Classifiers under Prior Shifts"
Add a description, image, and links to the distribution-shift topic page so that developers can more easily learn about it.
To associate your repository with the distribution-shift topic, visit your repo's landing page and select "manage topics."