相关论文: Co-Regularized Adversarial Learning for Multi-Doma…

The most successful multi-domain text classification (MDTC) approaches employ the shared-private paradigm to facilitate the enhancement of domain-invariant features through domain-specific attributes. Additionally, they employ adversarial…

In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align…

Using the shared-private paradigm and adversarial training has significantly improved the performances of multi-domain text classification (MDTC) models. However, there are two issues for the existing methods. First, instances from the…

In this paper, we propose conditional adversarial networks (CANs), a framework that explores the relationship between the shared features and the label predictions to impose more discriminability to the shared features, for multi-domain…

Multi-domain text classification (MDTC) endeavors to harness available resources from correlated domains to enhance the classification accuracy of the target domain. Presently, most MDTC approaches that embrace adversarial training and the…

Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains. Conventional approaches emphasize domain-shared information extraction and domain-private information…

Adversarial training has been instrumental in advancing multi-domain text classification (MDTC). Traditionally, MDTC methods employ a shared-private paradigm, with a shared feature extractor for domain-invariant knowledge and individual…

We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different domains. The core of our method is an…

Many text classification tasks are known to be highly domain-dependent. Unfortunately, the availability of training data can vary drastically across domains. Worse still, for some domains there may not be any annotated data at all. In this…

Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial learning based methods align source and target distributions…

Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimodal…

Recent advances on unsupervised domain adaptation (UDA) rely on adversarial learning to disentangle the explanatory and transferable features for domain adaptation. However, there are two issues with the existing methods. First, the…

Contrastive Reinforcement Learning (CRL) provides a promising framework for extracting useful structured representations from unlabeled interactions. By pulling together state-action pairs and their corresponding future states, while…

Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness can be improved when they are trained with these contaminated…

Entropy regularization is a popular method in reinforcement learning (RL). Although it has many advantages, it alters the RL objective of the original Markov Decision Process (MDP). Though divergence regularization has been proposed to…

Relational learning aims to make relation inference by exploiting the correlations among different types of entities. Exploring relational learning on multiple bipartite graphs has been receiving attention because of its popular…

Matching information across image and text modalities is a fundamental challenge for many applications that involve both vision and natural language processing. The objective is to find efficient similarity metrics to compare the similarity…

Modern high-dimensional methods often adopt the "bet on sparsity" principle, while in supervised multivariate learning statisticians may face "dense" problems with a large number of nonzero coefficients. This paper proposes a novel…

Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training of the model for improved robustness. While some recent works…

Multi-view multi-label learning frequently suffers from simultaneous feature absence and incomplete annotations, due to challenges in data acquisition and cost-intensive supervision. To tackle the complex yet highly practical problem while…