Timezone: »

On Representation Learning Under Class Imbalance
Ravid Shwartz-Ziv · Micah Goldblum · Yucen Li · C. Bayan Bruss · Andrew Gordon Wilson

Unlike carefully curated academic benchmarks, real-world datasets are often highly class-imbalanced, especially in safety-critical scenarios. Through extensive empirical investigation, we study a number of foundational learning behaviors for various models such as neural networks, gradient-boosted decision trees, and SVMs under class imbalance across a range of domains. Motivated by our observation that re-balancing class-imbalanced training data is ineffective, we show that several simple techniques for improving representation learning are effective in this setting: (1) self-supervised pre-training is insensitive to imbalance and can be used for feature learning before fine-tuning on labels; (2) Bayesian inference is effective because neural networks are especially underspecified under class imbalance; (3) flatness-seeking regularization pulls decision boundaries away from minority samples, especially when we seek minima that are particularly flat on the minority samples’ loss.

Author Information

Ravid Shwartz-Ziv (Hebrew University of Jerusalem)
Micah Goldblum (University of Maryland)
Yucen Li (New York University)
C. Bayan Bruss (Capital One)
Andrew Gordon Wilson (New York University)

More from the Same Authors