Tag: labels
-
Retraining strategy with evolving classes + imbalanced labels?
Retraining strategy with evolving classes + imbalanced labels? Hi all — I’m looking for advice on the best retraining strategy for a multi-class classifier in a setting where the label space can evolve. Right now I have about 6 labels, but I don’t know how many will show up over time, and some labels appear…
-
MLCBART: Multilabel Classification with Bayesian Additive Regression Trees
MLCBART: Multilabel Classification with Bayesian Additive Regression Trees arXiv:2601.08964v1 Announce Type: cross Abstract: Multilabel Classification (MLC) deals with the simultaneous classification of multiple binary labels. The task is challenging because, not only may there be arbitrarily different and complex relationships between predictor variables and each label, but associations among labels may exist even after accounting…
-
Do Labels Make AI Blind? Self-Supervision Solves the Age-Old Binding Problem
Do Labels Make AI Blind? Self-Supervision Solves the Age-Old Binding Problem A new NeurIPS 2025 paper shows how self-supervised learning imbues ViT with better image understanding than supervised learning The post Do Labels Make AI Blind? Self-Supervision Solves the Age-Old Binding Problem appeared first on Towards Data Science. Jonathan Williford Go to original source
-
Sequential Harmful Shift Detection Without Labels
Sequential Harmful Shift Detection Without Labels arXiv:2412.12910v1 Announce Type: new Abstract: We introduce a novel approach for detecting distribution shifts that negatively impact the performance of machine learning models in continuous production environments, which requires no access to ground truth data labels. It builds upon the work of Podkopaev and Ramdas [2022], who address scenarios…