相关论文: Denoising Distant Supervision for Relation Extract…

Unlike traditional learning to rank models that depend on hand-crafted features, neural representation learning models learn higher level features for the ranking task by training on large datasets. Their ability to learn new features…

Continual relation extraction (RE) aims to learn constantly emerging relations while avoiding forgetting the learned relations. Existing works store a small number of typical samples to re-train the model for alleviating forgetting.…

Accurate entity linkers have been produced for domains and languages where annotated data (i.e., texts linked to a knowledge base) is available. However, little progress has been made for the settings where no or very limited amounts of…

Recent advancements in masked image modeling (MIM) have made it a prevailing framework for self-supervised visual representation learning. The MIM pretrained models, like most deep neural network methods, remain vulnerable to adversarial…

Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is limited discussion on the potential noise in the time series,…

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…

Deep Neural Networks (DNNs) have often supplied state-of-the-art results in pattern recognition tasks. Despite their advances, however, the existence of adversarial examples have caught the attention of the community. Many existing works…

Relation extraction (RE) is an indispensable information extraction task in several disciplines. RE models typically assume that named entity recognition (NER) is already performed in a previous step by another independent model. Several…

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been…

This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are…

Real-world image noise removal is a long-standing yet very challenging task in computer vision. The success of deep neural network in denoising stimulates the research of noise generation, aiming at synthesizing more clean-noisy image pairs…

Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the…

We present an architecture for information extraction from text that augments an existing parser with a character-level neural network. The network is trained using a measure of consistency of extracted data with existing databases as a…

Network alignment has attracted widespread attention in various fields. However, most existing works mainly focus on the problem of label sparsity, while overlooking the issue of noise in network alignment, which can substantially undermine…

A powerful category of (invisible) data poisoning attacks modify a subset of training examples by small adversarial perturbations to change the prediction of certain test-time data. Existing defense mechanisms are not desirable to deploy in…

In the last few years, image denoising has benefited a lot from the fast development of neural networks. However, the requirement of large amounts of noisy-clean image pairs for supervision limits the wide use of these models. Although…

Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases. Adversarial learning may help models ignore sensitive biases and spurious correlations in data. We evaluate whether adversarial…

Deep neural models for relation extraction tend to be less reliable when perfectly labeled data is limited, despite their success in label-sufficient scenarios. Instead of seeking more instance-level labels from human annotators, here we…

Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled data is scarce. In this paper, we introduce a novel…