English
Related papers

Related papers: Improving Scheduled Sampling with Elastic Weight C…

200 papers

Sample selection is a straightforward technique to combat noisy labels, aiming to prevent mislabeled samples from degrading the robustness of neural networks. However, existing methods mitigate compounding selection bias either by…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Kangye Ji , Fei Cheng , Zeqing Wang , Qichang Zhang , Bohu Huang

Sampling complex free energy surfaces is one of the main challenges of modern atomistic simulation methods. The presence of kinetic bottlenecks in such surfaces often renders a direct approach useless. A popular strategy is to identify a…

Computational Physics · Physics 2019-09-25 Luigi Bonati , Yue-Yu Zhang , Michele Parrinello

We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a…

Denoising Diffusion Probabilistic Models have shown an impressive generation quality, although their long sampling chain leads to high computational costs. In this paper, we observe that a long sampling chain also leads to an error…

Machine Learning · Computer Science 2023-06-21 Mang Ning , Enver Sangineto , Angelo Porrello , Simone Calderara , Rita Cucchiara

Pretraining language models on large text corpora is a common practice in natural language processing. Fine-tuning of these models is then performed to achieve the best results on a variety of tasks. In this paper, we investigate the…

Computation and Language · Computer Science 2024-04-03 Philip Kenneweg , Alexander Schulz , Sarah Schröder , Barbara Hammer

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Lu Yu , Bartłomiej Twardowski , Xialei Liu , Luis Herranz , Kai Wang , Yongmei Cheng , Shangling Jui , Joost van de Weijer

Machine learning models achieve state-of-the-art performance on many supervised learning tasks. However, prior evidence suggests that these models may learn to rely on shortcut biases or spurious correlations (intuitively, correlations that…

Machine Learning · Computer Science 2021-08-31 Sindhu C. M. Gowda , Shalmali Joshi , Haoran Zhang , Marzyeh Ghassemi

Auto-regressive sequence-to-sequence models with attention mechanisms have achieved state-of-the-art performance in various tasks including Text-To-Speech (TTS) and Neural Machine Translation (NMT). The standard training approach, teacher…

Computation and Language · Computer Science 2021-04-06 Qingyun Dou , Yiting Lu , Potsawee Manakul , Xixin Wu , Mark J. F. Gales

Non-parametric maximum likelihood estimation encompasses a group of classic methods to estimate distribution-associated functions from potentially censored and truncated data, with extensive applications in survival analysis. These methods,…

Methodology · Statistics 2021-08-05 Justin D. Tubbs , Lane Guolan Chen , Thuan Quoc Thach , Pak C. Sham

Time series prediction is often complicated by distribution shift which demands adaptive models to accommodate time-varying distributions. We frame time series prediction under distribution shift as a weighted empirical risk minimisation…

Machine Learning · Computer Science 2022-07-26 Stefanos Bennett , Jase Clarkson

Recently, large language and vision models have shown strong performance, but due to high pre-training and fine-tuning costs, research has shifted towards faster training via dataset pruning. Previous methods used sample loss as an…

Machine Learning · Computer Science 2026-01-13 Jinying Xiao , Ping Li , Jie Nie , Bin Ji , Shasha Li , Xiaodong Liu , Jun Ma , Qingbo Wu , Jie Yu

Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance…

Machine Learning · Computer Science 2026-04-13 Zhuang Qi , Ying-Peng Tang , Lei Meng , Guoqing Chao , Lei Wu , Han Yu , Xiangxu Meng

This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data from the target domain to alleviate the performance degradation due to the distribution shift…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Sungha Choi , Seunghan Yang , Seokeon Choi , Sungrack Yun

In continual time series analysis using neural networks, catastrophic forgetting (CF) of previously learned models when training on new data domains has always been a significant challenge. This problem is especially challenging in vehicle…

Machine Learning · Computer Science 2025-04-08 Arvin Hosseinzadeh , Ladan Khoshnevisan , Mohammad Pirani , Shojaeddin Chenouri , Amir Khajepour

A large obstacle to deploying deep learning models in practice is the process of updating models post-deployment (ideally, frequently). Deep neural networks can cost many thousands of dollars to train. When new data comes in the pipeline,…

Machine Learning · Computer Science 2023-06-21 Rich Harang , Hillary Sanders

This article focuses on large language models (LLMs) fine-tuning in the scarce data regime (also known as the "few-shot" learning setting). We propose a method to increase the generalization capabilities of LLMs based on neural network…

Machine Learning · Computer Science 2023-10-25 Louis Falissard , Vincent Guigue , Laure Soulier

Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for…

Neural language models do not scale well when the vocabulary is large. Noise-contrastive estimation (NCE) is a sampling-based method that allows for fast learning with large vocabularies. Although NCE has shown promising performance in…

Computation and Language · Computer Science 2017-09-25 Farhana Ferdousi Liza , Marek Grzes

Learning with noisy labels aims to ensure model generalization given a label-corrupted training set. The sample selection strategy achieves promising performance by selecting a label-reliable subset for model training. In this paper, we…

Machine Learning · Computer Science 2025-04-11 Qi Wei , Lei Feng , Haobo Wang , Bo An

Sequence-to-sequence models based on LSTM and GRU are a most popular choice for forecasting time series data reaching state-of-the-art performance. Training such models can be delicate though. The two most common training strategies within…

Machine Learning · Computer Science 2022-10-18 Philipp Teutsch , Patrick Mäder