English
Related papers

Related papers: Memorisation versus Generalisation in Pre-trained …

200 papers

Recently deep neural networks have shown their capacity to memorize training data, even with noisy labels, which hurts generalization performance. To mitigate this issue, we provide a simple but effective baseline method that is robust to…

Machine Learning · Computer Science 2019-09-30 Yucen Luo , Jun Zhu , Tomas Pfister

Very large deep learning models trained using gradient descent are remarkably resistant to memorization given their huge capacity, but are at the same time capable of fitting large datasets of pure noise. Here methods are introduced by…

Machine Learning · Computer Science 2022-12-22 Benjamin L. Badger

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

Machine Learning · Computer Science 2025-06-27 Fei Wang , Baochun Li

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Despite the success of language models using neural networks, it remains unclear to what extent neural models have the generalization ability to perform inferences. In this paper, we introduce a method for evaluating whether neural models…

Computation and Language · Computer Science 2020-05-05 Hitomi Yanaka , Koji Mineshima , Daisuke Bekki , Kentaro Inui

Pre-trained language models have recently emerged as a powerful tool for fine-tuning a variety of language tasks. Ideally, when models are pre-trained on large amount of data, they are expected to gain implicit knowledge. In this paper, we…

Computation and Language · Computer Science 2023-06-22 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kühnberger

Transformers have the capacity to act as supervised learning algorithms: by properly encoding a set of labeled training ("in-context") examples and an unlabeled test example into an input sequence of vectors of the same dimension, the…

Machine Learning · Computer Science 2024-12-16 Spencer Frei , Gal Vardi

Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art. In this paper we explore the efficiency of various pre-trained language models. We pre-train a list of…

Computation and Language · Computer Science 2023-07-27 Tong Guo

Incorporating large-scale pre-trained models with the prototypical neural networks is a de-facto paradigm in few-shot named entity recognition. Existing methods, unfortunately, are not aware of the fact that embeddings from pre-trained…

Computation and Language · Computer Science 2022-11-08 Youcheng Huang , Wenqiang Lei , Jie Fu , Jiancheng Lv

Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in providing theoretical guarantees for the performance of the…

Machine Learning · Computer Science 2020-11-17 Baharan Mirzasoleiman , Kaidi Cao , Jure Leskovec

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios, data labels are…

Computation and Language · Computer Science 2023-11-03 Song Wang , Zhen Tan , Ruocheng Guo , Jundong Li

In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is…

Computation and Language · Computer Science 2019-04-03 Debjit Paul , Mittul Singh , Michael A. Hedderich , Dietrich Klakow

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Tsung-Ming Tai , Yun-Jie Jhang , Wen-Jyi Hwang

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There…

Machine Learning · Computer Science 2019-04-15 Junnan Li , Yongkang Wong , Qi Zhao , Mohan Kankanhalli

The performance of a model trained with noisy labels is often improved by simply \textit{retraining} the model with its \textit{own predicted hard labels} (i.e., 1/0 labels). Yet, a detailed theoretical characterization of this phenomenon…

Quantum machine learning models have shown successful generalization performance even when trained with few data. In this work, through systematic randomization experiments, we show that traditional approaches to understanding…

Quantum Physics · Physics 2024-03-14 Elies Gil-Fuster , Jens Eisert , Carlos Bravo-Prieto

We show that in language learning, contrary to received wisdom, keeping exceptional training instances in memory can be beneficial for generalization accuracy. We investigate this phenomenon empirically on a selection of benchmark natural…

Computation and Language · Computer Science 2007-05-23 Walter Daelemans , Antal van den Bosch , Jakub Zavrel

Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning with noisy labels often rely on the availability of a clean subset of data. By…

Machine Learning · Computer Science 2025-11-27 David Szczecina , Nicholas Pellegrino , Paul Fieguth

Pretrained Language Models (LMs) have demonstrated ability to perform numerical reasoning by extrapolating from a few examples in few-shot settings. However, the extent to which this extrapolation relies on robust reasoning is unclear. In…

Computation and Language · Computer Science 2023-03-17 Yasaman Razeghi , Robert L. Logan , Matt Gardner , Sameer Singh

Recent studies on the memorization effects of deep neural networks on noisy labels show that the networks first fit the correctly-labeled training samples before memorizing the mislabeled samples. Motivated by this early-learning…

Machine Learning · Computer Science 2021-09-07 Yangdi Lu , Yang Bo , Wenbo He
‹ Prev 1 3 4 5 6 7 10 Next ›