Grokked Models are Better Unlearners
Grokking-delayed generalization that emerges well after a model has fit the training data-has been linked to robustness and representation quality. We ask whether this training regime also helps with machine unlearning, i.e., removing the influence of specified data without full retraining. We compare applying standard unlearning methods before versus after the grokking transition across vision (CNNs/ResNets on CIFAR, SVHN, and ImageNet) and language (a transformer on a TOFU-style setup). Starting from grokked checkpoints consistently yields (i) more efficient forgetting (fewer updates to reach a target forget level), (ii) less collateral damage (smaller drops on retained and test performance), and (iii) more stable updates across seeds, relative to early-stopped counterparts under identical unlearning algorithms. Analyses of features and curvature further suggest that post-grokking models learn more modular representations with reduced gradient alignment between forget and retain subsets, which facilitates selective forgetting. Our results highlight when a model is trained (pre- vs. post-grokking) as an orthogonal lever to how unlearning is performed, providing a practical recipe to improve existing unlearning methods without altering their algorithms.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers
While Large Language Models (LLMs) excel at factual retrieval, they often struggle with the "curse of two-hop reasoning" in compositional tasks. Recent research suggests that parameter-sharing transformers can bridge thi…
Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
Grokking has been actively explored to reveal the mystery of delayed generalization and identifying interpretable representations and algorithms inside the grokked models is a suggestive hint to understanding its mechani…
When Data Falls Short: Grokking Below the Critical Threshold
In this paper, we investigate the phenomenon of grokking, where models exhibit delayed generalization following overfitting on training data. We focus on data-scarce regimes where the number of training samples falls bel…
Knowledge DistillationContinual PretrainingDimensional Criticality at Grokking Across MLPs and Transformers
Abrupt transitions between distinct dynamical regimes are a hallmark of complex systems. Grokking in deep neural networks provides a striking example -- an abrupt transition from memorization to generalization long after…
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with. Focusing on two representative reasoning types, composition and co…