Related papers: Noisy Correspondence Learning with Self-Reinforcin…

In the field of multimodal sentiment analysis (MSA), a few studies have leveraged the inherent modality correlation information stored in samples for self-supervised learning. However, they feed the training pairs in a random order without…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

Implicit feedback, employed in training recommender systems, unavoidably confronts noise due to factors such as misclicks and position bias. Previous studies have attempted to identify noisy samples through their diverged data patterns,…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Deep neural networks have incredible capacity and expressibility, and can seemingly memorize any training set. This introduces a problem when training in the presence of noisy labels, as the noisy examples cannot be distinguished from clean…

In recent years, large language models (LLM) have made significant progress in the task of generation error correction (GER) for automatic speech recognition (ASR) post-processing. However, in complex noisy environments, they still face…

Ensemble Learning methods combine multiple algorithms performing the same task to build a group with superior quality. These systems are well adapted to the distributed setup, where each peer or machine of the network hosts one algorithm…

The emergence of large-scale automatic speech recognition (ASR) models such as Whisper has greatly expanded their adoption across diverse real-world applications. Ensuring robustness against even minor input perturbations is therefore…

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training…

The memorization effect of deep neural networks (DNNs) plays a pivotal role in recent label noise learning methods. To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of…

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious…

Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two…

In learning tasks with label noise, improving model robustness against overfitting is a pivotal challenge because the model eventually memorizes labels, including the noisy ones. Identifying the samples with noisy labels and preventing the…

We introduce ANTIDOTE, a new class of objectives for learning under noisy labels which are defined in terms of a relaxation over an information-divergence neighborhood. Using convex duality, we provide a reformulation as an adversarial…

We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to…

Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address…

Cross-modal hashing (CMH) has appeared as a popular technique for cross-modal retrieval due to its low storage cost and high computational efficiency in large-scale data. Most existing methods implicitly assume that multi-modal data is…

Either human annotation or rule based automatic labeling is an effective method to augment data for relation extraction. However, the inevitable wrong labeling problem for example by distant supervision may deteriorate the performance of…

Speech emotion recognition (SER) often experiences reduced performance due to background noise. In addition, making a prediction on signals with only background noise could undermine user trust in the system. In this study, we propose a…