Characterizing Datapoints via Second-Split Forgetting
Researchers investigating example hardness have increasingly focused on the dynamics by which neural networks learn and forget examples throughout training. Popular metrics derived from these dynamics include (i) the epoch at which examples are first correctly classified; (ii) the number of times their predictions flip during training; and (iii) whether their prediction flips if they are held out. However, these metrics do not distinguish among examples that are hard for distinct reasons, such as membership in a rare subpopulation, being mislabeled, or belonging to a complex subpopulation. In this paper, we propose $second$-$split$ $forgetting$ $time$ (SSFT), a complementary metric that tracks the epoch (if any) after which an original training example is forgotten as the network is fine-tuned on a randomly held out partition of the data. Across multiple benchmark datasets and modalities, we demonstrate that $mislabeled$ examples are forgotten quickly, and seemingly $rare$ examples are forgotten comparatively slowly. By contrast, metrics only considering the first split learning dynamics struggle to differentiate the two. At large learning rates, SSFT tends to be robust across architectures, optimizers, and random seeds. From a practical standpoint, the SSFT can (i) help to identify mislabeled samples, the removal of which improves generalization; and (ii) provide insights about failure modes. Through theoretical analysis addressing overparameterized linear models, we provide insights into how the observed phenomena may arise. Code for reproducing our experiments can be found here: https://github.com/pratyushmaini/ssft
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks
In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual lear…
Continual LearningRESTOR: Knowledge Recovery through Machine Unlearning
Large language models trained on web-scale corpora can memorize undesirable datapoints such as incorrect facts, copyrighted content or sensitive data. Recently, many machine unlearning algorithms have been proposed that …
Machine UnlearningSubspace Geometry Governs Catastrophic Forgetting in Low-Rank Adaptation
Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for adapting large pre-trained models, yet its behavior under continual learning remains poorly understood. We present a geometric theory character…
parameter-efficient fine-tuningContinual LearningMeasuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
In continual learning scenarios, catastrophic forgetting of previously learned tasks is a critical issue, making it essential to effectively measure such forgetting. Recently, there has been growing interest in focusing …
Continual LearningNegotiated Representations to Prevent Forgetting in Machine Learning Applications
Catastrophic forgetting is a significant challenge in the field of machine learning, particularly in neural networks. When a neural network learns to perform well on a new task, it often forgets its previously acquired k…
Continual LearningImage ClassificationSplit-CIFAR-10Split-MNIST