Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling

[2504.07031] Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2504.07031 (cs) [Submitted on 9 Apr 2025 ( v1 ), last revised 10 Apr 2026 (this version, v2)] Title: Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling Authors: Pawel Pukowski , Venet Osmani View a PDF of the paper titled Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling, by Pawel Pukowski and Venet Osmani View PDF HTML (experimental) Abstract: Class-bias, that is class-wise performance disparities, is typically attributed to data imbalance and addressed through frequency-based resampling. However, we demonstrate that substantial bias persists even in perfectly balanced datasets, proving that class frequency alone cannot explain unequal model performance. We investigate these disparities through the lens of class-level learning difficulty and propose Hardness-Based Resampling (HBR), a strategy that leverages hardness estimates to guide data selection. To better capture these effects, we introduce an evaluation protocol that complements global metrics with gap- and dispersion-based measures. Our experiments show that HBR significantly reduces recall gaps, by up to 32% on CIFAR-10 and 16% on CIFAR-100, outperforming standard frequency-based resampling. We further show that we can improve fairness outcomes by selectively using the hardest samples from a state-of-the-art diffusion model, rather than randomly selecting them. These findings demonstrate that data balance alone is insufficient to mitigate class bias, necessitating a shift toward hardness-aware approaches. Comments: Submitted to Springer ML Subjects: Machine Learning (cs.LG) Cite as: arXiv:2504.07031 [cs.LG] (or arXiv:2504.07031v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2504.07031 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Pawel Pukowski [ view email ] [v1] Wed, 9 Apr 2025 16:45:57 UTC (2,643 KB) [v2] Fri, 10 Apr 2026 10:42:17 UTC (4,668 KB) Full-text links: Access Paper: View a PDF of the paper titled Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling, by Pawel Pukowski and Venet Osmani View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2025-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Improving Fairness in Doubly Imbalanced Datasets.#653528
• Exact Reformulation and Optimization for Direct Metric Optimization in Binary Imbalanced Classification#629799
• FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning#441751
• TILBench: A Systematic Benchmark for Tabular Imbalanced Learning Across Data Regimes#187339
• Hardness of Learning with Physical Rounding and Noise from Learning With Errors#445657