English
Related papers

Related papers: Energy Aligning for Biased Models

200 papers

Real-world datasets often encode stereotypes and societal biases. Such biases can be implicitly captured by trained models, leading to biased predictions and exacerbating existing societal preconceptions. Existing debiasing methods, such as…

Machine Learning · Computer Science 2022-05-06 Aili Shen , Xudong Han , Trevor Cohn , Timothy Baldwin , Lea Frermann

Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough data, the classification performance gain is marginal with…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Yanbiao Ma , Licheng Jiao , Fang Liu , Yuxin Li , Shuyuan Yang , Xu Liu

Due to the inherent imbalance in real-world datasets, na\"ive Empirical Risk Minimization (ERM) tends to bias the learning process towards the majority classes, hindering generalization to minority classes. To rebalance the learning…

Machine Learning · Computer Science 2025-12-09 Zitai Wang , Qianqian Xu , Zhiyong Yang , Zhikang Xu , Linchao Zhang , Xiaochun Cao , Qingming Huang

The accuracy of any machine learning potential can only be as good as the data used in the fitting process. The most efficient model therefore selects the training data that will yield the highest accuracy compared to the cost of obtaining…

Chemical Physics · Physics 2020-07-21 Anders S. Christensen , O. Anatole von Lilienfeld

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of…

Machine Learning · Computer Science 2022-10-18 Xudong Han , Aili Shen , Trevor Cohn , Timothy Baldwin , Lea Frermann

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…

Machine Learning · Computer Science 2024-02-20 Huafeng Liu , Mengmeng Sheng , Zeren Sun , Yazhou Yao , Xian-Sheng Hua , Heng-Tao Shen

Data imbalance is a common problem in machine learning that can have a critical effect on the performance of a model. Various solutions exist but their impact on the convergence of the learning dynamics is not understood. Here, we elucidate…

Machine Learning · Statistics 2024-02-20 Emanuele Francazi , Marco Baity-Jesi , Aurelien Lucchi

Deep structured-prediction energy-based models combine the expressive power of learned representations and the ability of embedding knowledge about the task at hand into the system. A common way to learn parameters of such models consists…

Machine Learning · Computer Science 2019-03-01 Aleksandr Shevchenko , Anton Osokin

Imbalanced data are frequently encountered in real-world classification tasks. Previous works on imbalanced learning mostly focused on learning with a minority class of few samples. However, the notion of imbalance also applies to cases…

Machine Learning · Computer Science 2024-09-09 Yin Jin , Ningtao Wang , Ruofan Wu , Pengfei Shi , Xing Fu , Weiqiang Wang

Data rebalancing techniques, including oversampling and undersampling, are a common approach to addressing the challenges of imbalanced data. To tackle unresolved problems related to both oversampling and undersampling, we propose a new…

Machine Learning · Computer Science 2025-07-11 Karen Medlin , Sven Leyffer , Krishnan Raghavan

In distributed and federated learning, heterogeneity across data sources remains a major obstacle to effective model aggregation and convergence. We focus on feature heterogeneity and introduce energy distance as a sensitive measure for…

Machine Learning · Statistics 2025-01-28 Mengchen Fan , Baocheng Geng , Roman Shterenberg , Joseph A. Casey , Zhong Chen , Keren Li

We address the problem of active learning under label shift: when the class proportions of source and target domains differ. We introduce a "medial distribution" to incorporate a tradeoff between importance weighting and class-balanced…

Machine Learning · Computer Science 2021-03-01 Eric Zhao , Anqi Liu , Animashree Anandkumar , Yisong Yue

Imbalanced classification problems are extremely common in natural language processing and are solved using a variety of resampling and filtering techniques, which often involve making decisions on how to select training data or decide…

Computation and Language · Computer Science 2022-09-02 Ryan Muther , David Smith

This paper proposes the divergence triangle as a framework for joint training of generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly…

Machine Learning · Statistics 2019-02-01 Tian Han , Erik Nijkamp , Xiaolin Fang , Mitch Hill , Song-Chun Zhu , Ying Nian Wu

Federated learning aims to learn a global model collaboratively while the training data belongs to different clients and is not allowed to be exchanged. However, the statistical heterogeneity challenge on non-IID data, such as class…

Machine Learning · Computer Science 2023-04-12 Yunheng Shen , Haoxiang Wang , Hairong Lv

Federated learning (FL) enables collaborative model training across distributed devices while preserving data privacy. However, balancing energy efficiency and fair participation while ensuring high model accuracy remains challenging in…

Machine Learning · Computer Science 2025-11-20 Ouiame Marnissi , Hajar EL Hammouti , El Houcine Bergou

When faced with severely imbalanced binary classification problems, we often train models on bootstrapped data in which the number of instances of each class occur in a more favorable ratio, e.g., one. We view algorithmic inequity through…

Machine Learning · Statistics 2021-08-17 Harish S. Bhat , Majerle E. Reeves , Sidra Goldman-Mellor

Class imbalance (CI) is a longstanding problem in machine learning, slowing down training and reducing performances. Although empirical remedies exist, it is often unclear which ones work best and when, due to the lack of an overarching…

Machine Learning · Computer Science 2025-08-06 F. S. Pezzicoli , V. Ros , F. P. Landes , M. Baity-Jesi

Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-02 XIn Zhang , Yuqi Song , Fei Zuo , Xiaofeng Wang

In real world datasets, particular groups are under-represented, much rarer than others, and machine learning classifiers will often preform worse on under-represented populations. This problem is aggravated across many domains where…

Machine Learning · Computer Science 2023-02-10 Arghya Datta , S. Joshua Swamidass