English
Related papers

Related papers: Dataset balancing can hurt model performance

200 papers

Many set selection and ranking algorithms have recently been enhanced with diversity constraints that aim to explicitly increase representation of historically disadvantaged populations, or to improve the overall representativeness of the…

Artificial Intelligence · Computer Science 2019-06-06 Ke Yang , Vasilis Gkatzelis , Julia Stoyanovich

The increased availability of medical data has significantly impacted healthcare by enabling the application of machine / deep learning approaches in various instances. However, medical datasets are usually small and scattered across…

Meta-learning is a popular framework for learning with limited data in which an algorithm is produced by training over multiple few-shot learning tasks. For classification problems, these tasks are typically constructed by sampling a small…

Machine Learning · Computer Science 2021-10-08 Amrith Setlur , Oscar Li , Virginia Smith

To achieve state-of-the-art performance, one still needs to train NER models on large-scale, high-quality annotated data, an asset that is both costly and time-intensive to accumulate. In contrast, real-world applications often resort to…

Computation and Language · Computer Science 2023-10-26 Zhendong Chu , Ruiyi Zhang , Tong Yu , Rajiv Jain , Vlad I Morariu , Jiuxiang Gu , Ani Nenkova

In the recent years, singing voice separation systems showed increased performance due to the use of supervised training. The design of training datasets is known as a crucial factor in the performance of such systems. We investigate on how…

Sound · Computer Science 2019-06-07 Laure Prétet , Romain Hennequin , Jimena Royo-Letelier , Andrea Vaglio

Source separation is the task to separate an audio recording into individual sound sources. Source separation is fundamental for computational auditory scene analysis. Previous work on source separation has focused on separating particular…

Sound · Computer Science 2020-02-07 Qiuqiang Kong , Yuxuan Wang , Xuchen Song , Yin Cao , Wenwu Wang , Mark D. Plumbley

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50% to 80%) is used for training and the rest for validation. In many problems, however, the data is highly imbalanced in regard to different…

Machine Learning · Computer Science 2020-04-21 Xiaowei Gu , Plamen P Angelov , Eduardo Almeida Soares

Robots should be able to learn complex behaviors from human demonstrations. In practice, these human-provided datasets are inevitably imbalanced: i.e., the human demonstrates some subtasks more frequently than others. State-of-the-art…

Robotics · Computer Science 2026-01-06 Sagar Parekh , Heramb Nemlekar , Dylan P. Losey

Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific subpopulations. Prior work has shown that common evaluation…

Machine Learning · Computer Science 2026-04-30 Taylor Maxson , Roberto Corizzo , Yaning Wu , Nathalie Japkowicz , Colin Bellinger

Many datasets and approaches in ambient sound analysis use weakly labeled data.Weak labels are employed because annotating every data sample with a strong label is too expensive.Yet, their impact on the performance in comparison to strong…

Sound · Computer Science 2020-12-08 Nicolas Turpault , Romain Serizel , Emmanuel Vincent

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

Machine learning models are routinely used to support decisions that affect individuals -- be it to screen a patient for a serious illness or to gauge their response to treatment. In these tasks, we are limited to learning models from…

Machine Learning · Computer Science 2025-06-10 Sujay Nagaraj , Yang Liu , Flavio P. Calmon , Berk Ustun

Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-22 Jiaxu Chen , Jing Hao , Kai Chen , Di Xie , Shicai Yang , Shiliang Pu

Teaching is one of the most important factors affecting any education system. Many research efforts have been conducted to facilitate the presentation modes used by instructors in classrooms as well as provide means for students to review…

Machine Learning · Computer Science 2012-01-16 Marian George , Moustafa Youssef

Human biases have been shown to influence the performance of models and algorithms in various fields, including Natural Language Processing. While the study of this phenomenon is garnering focus in recent years, the available resources are…

Computation and Language · Computer Science 2024-08-15 Ana Sofia Evans , Helena Moniz , Luísa Coheur

We introduce PodcastMix, a dataset formalizing the task of separating background music and foreground speech in podcasts. We aim at defining a benchmark suitable for training and evaluating (deep learning) source separation models. To that…

Sound · Computer Science 2022-07-18 Nicolás Schmidt , Jordi Pons , Marius Miron

Despite the fact that data imbalance is becoming more and more common in real-world Spoken Language Understanding (SLU) applications, it has not been studied extensively in the literature. To the best of our knowledge, this paper presents…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-07 Judith Gaspers , Quynh Do , Fabian Triefenbach

Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions,…

Machine Learning · Computer Science 2023-12-06 Ravid Shwartz-Ziv , Micah Goldblum , Yucen Lily Li , C. Bayan Bruss , Andrew Gordon Wilson

Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We…

Machine Learning · Computer Science 2025-01-22 Kavita Selva , Satita Vittayaareekul , Brando Miranda

Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes, making fair assessment of classifiers a challenging task. Metrics such as Balanced Accuracy are commonly used to evaluate a…

‹ Prev 1 3 4 5 6 7 10 Next ›