Poster
The Pitfalls of Memorization: When Memorization Hurts Generalization
Reza Bayat · Mohammad Pezeshki · Elvis Dohmatob · David Lopez-Paz · Pascal Vincent
Hall 3 + Hall 2B #304
[
Abstract
]
Sat 26 Apr midnight PDT
— 2:30 a.m. PDT
Abstract:
Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explanations. This behavior leads to poor generalization when the learned explanations rely on spurious correlations. In this work, we formalize the interplay between memorization and generalizationthe interplay between memorization and generalization, showing that spurious correlations would particularly lead to poor generalization when are combined with memorization. Memorization can reduce training loss to zero, leaving no incentive to learn robust, generalizable patterns. To address this, we propose memorization-aware trainingmemorization-aware training (MAT), which uses held-out predictions as a signal of memorization to shift a model's logits. MAT encourages learning robust patterns invariant across distributions, improving generalization under distribution shifts.
Live content is unavailable. Log in and register to view live content