236 citations · 284 across the 18 of their papers we have counts for
15 papers · 1 filter
Data Heterogeneity Modeling for Trustworthy Machine Learning
Jiashuo Liu, Peng Cui
Data heterogeneity plays a pivotal role in determining the performance of machine learning (ML) systems. Traditional algorithms, which are typically designed to optimize average pe…
DRO: A Python Library for Distributionally Robust Optimization in Machine Learning
Jiashuo Liu, Tianyu Wang, Henry Lam +2
We introduce dro, an open-source Python library for distributionally robust optimization (DRO) for regression and classification problems. The library implements 14 DRO formulation…
Error Slice Discovery via Manifold Compactness
Han Yu, Hao Zou, Jiashuo Liu +4
Despite the great performance of deep learning models in many areas, they still make mistakes and underperform on certain subsets of data, i.e. error slices. Given a trained model,…
LLM Embeddings Improve Test-time Adaptation to Tabular -Shifts
Yibo Zeng, Jiashuo Liu, Henry Lam +1
For tabular datasets, the change in the relationship between the label and covariates (-shifts) is common due to missing variables (a.k.a. confounders). Since it is impossible…
Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph
Weihuang Zheng, Jiashuo Liu, Jiaxing Li +3
Graph Neural Networks (GNNs) are widely used for node classification tasks but often fail to generalize when training and test nodes come from different distributions, limiting the…
Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
Jiayun Wu, Jiashuo Liu, Peng Cui +1
We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration, a criterion that ensures a predictor is calibrated across a fa…
A Survey on Evaluation of Out-of-Distribution Generalization
Han Yu, Jiashuo Liu, Xingxuan Zhang +2
Machine learning models, while progressively advanced, rely heavily on the IID assumption, which is often unfulfilled in practice due to inevitable distribution shifts. This render…
Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications
Jiashuo Liu, Jiayun Wu, Tianyu Wang +3
Machine learning algorithms minimizing average risk are susceptible to distributional shifts. Distributionally Robust Optimization (DRO) addresses this issue by optimizing the wors…
Rethinking Distribution Shifts: Empirical Analysis and Modeling for Tabular Data
Tianyu Wang, Jiashuo Liu, Peng Cui +1
Different distribution shifts require different interventions, and algorithms must be grounded in the specific shifts they address. However, methodological development for robust a…
Meta Adaptive Task Sampling for Few-Domain Generalization
Zheyan Shen, Han Yu, Peng Cui +4
To ensure the out-of-distribution (OOD) generalization performance, traditional domain generalization (DG) methods resort to training on data from multiple sources with different u…
Rethinking the Evaluation Protocol of Domain Generalization
Han Yu, Xingxuan Zhang, Renzhe Xu +3
Domain generalization aims to solve the challenge of Out-of-Distribution (OOD) generalization by leveraging common knowledge learned from multiple training domains to generalize to…
Predictive Heterogeneity: Measures and Applications
Jiashuo Liu, Jiayun Wu, Bo Li +1
As an intrinsic and fundamental property of big data, data heterogeneity exists in a variety of real-world applications, such as precision medicine, autonomous driving, financial a…
Enhancing Distributional Stability among Sub-populations
Jiashuo Liu, Jiayun Wu, Jie Peng +4
Enhancing the stability of machine learning algorithms under distributional shifts is at the heart of the Out-of-Distribution (OOD) Generalization problem. Derived from causal lear…
Kernelized Heterogeneous Risk Minimization
Jiashuo Liu, Zheyuan Hu, Peng Cui +2
The ability to generalize under distributional shifts is essential to reliable machine learning, while models optimized with empirical risk minimization usually fail on non-…
Towards Out-Of-Distribution Generalization: A Survey
Jiashuo Liu, Zheyan Shen, Yue He +4
Traditional machine learning paradigms are based on the assumption that both training and test data follow the same statistical pattern, which is mathematically referred to as Inde…