Multi-Domain Learning From Insufficient Annotations

by   Rui He, et al.

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 preservation, following the shared-private framework (SP models), which offers significant advantages over single-domain learning. However, the limited availability of annotated data in each domain considerably hinders the effectiveness of conventional supervised MDL approaches in real-world applications. In this paper, we introduce a novel method called multi-domain contrastive learning (MDCL) to alleviate the impact of insufficient annotations by capturing both semantic and structural information from both labeled and unlabeled data.Specifically, MDCL comprises two modules: inter-domain semantic alignment and intra-domain contrast. The former aims to align annotated instances of the same semantic category from distinct domains within a shared hidden space, while the latter focuses on learning a cluster structure of unlabeled instances in a private hidden space for each domain. MDCL is readily compatible with many SP models, requiring no additional model parameters and allowing for end-to-end training. Experimental results across five textual and image multi-domain datasets demonstrate that MDCL brings noticeable improvement over various SP models.Furthermore, MDCL can further be employed in multi-domain active learning (MDAL) to achieve a superior initialization, eventually leading to better overall performance.


page 1

page 2

page 3

page 4


A Robust Contrastive Alignment Method For Multi-Domain Text Classification

Multi-domain text classification can automatically classify texts in var...

Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data

In many real-world machine learning applications, samples belong to a se...

Dual Adversarial Co-Learning for Multi-Domain Text Classification

In this paper we propose a novel dual adversarial co-learning approach f...

MAMDR: A Model Agnostic Learning Method for Multi-Domain Recommendation

Large-scale e-commercial platforms in the real-world usually contain var...

Addressing Limited Data for Textual Entailment Across Domains

We seek to address the lack of labeled data (and high cost of annotation...

Domain-Specific Bias Filtering for Single Labeled Domain Generalization

Domain generalization (DG) utilizes multiple labeled source datasets to ...

Improving Contrastive Learning on Visually Homogeneous Mars Rover Images

Contrastive learning has recently demonstrated superior performance to s...

Please sign up or login with your details

Forgot password? Click here to reset