paper-with-me

Papers

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

2022-04-05 · WASSA (ACL) 2022 5 · Zixuan Ke, Mohammad Kachuee, Sungjin Lee

In many real-world machine learning applications, samples belong to a set of domains e.g., for product reviews each review belongs to a product category. In this paper, we study multi-domain imbalanced learning (MIL), the scenario that there is imbalance not only in classes but also in domains. In the MIL setting, different domains exhibit different patterns and there is a varying degree of similarity and divergence among domains posing opportunities and challenges for transfer learning especially when faced with limited or insufficient training data. We propose a novel domain-aware contrastive knowledge transfer method called DCMI to (1) identify the shared domain knowledge to encourage positive transfer among similar domains (in particular from head domains to tail domains); (2) isolate the domain-specific knowledge to minimize the negative transfer from dissimilar domains. We evaluated the performance of DCMI on three different datasets showing significant improvements in different MIL scenarios.

📄 PDF Abstract BibTeX arXiv:2204.01916

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation

2023-01-01 · CVPR 2023 1 · Yixin Zhang, Zilei Wang, Weinan He

This work focuses on a practical knowledge transfer task defined as Source-Free Unsupervised Domain Adaptation (SFUDA), where only a well-trained source model and unlabeled target data are available. To fully utilize…

Contrastive LearningDomain AdaptationTransfer LearningUnsupervised Domain Adaptation

Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models

2026-05-25 · Zongji Yu, Wenshui Luo, Yiliu Sun, Hao Fang 외 arxiv

Post-training has significantly enhanced the reasoning capability of Large Reasoning Models (LRMs), especially with Reinforcement Learning (RL) like Group Relative Policy Optimization (GRPO). However, GRPO-style RL metho…

Reinforcement Learning

BotaCLIP: Contrastive Learning for Botany-Aware Representation of Earth Observation Data

2025-11-26 · Selene Cerna, Sara Si-Moussi, Wilfried Thuiller, Hadrien Hendrikx 외 arxiv

Foundation models have demonstrated a remarkable ability to learn rich, transferable representations across diverse modalities such as images, text, and audio. In modern machine learning pipelines, these representations …

Representation LearningContrastive Learning

Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning

2022-05-01 · ACL 2022 5 · Yutao Mou, Keqing He, Yanan Wu, Zhiyuan Zeng 외

Discovering Out-of-Domain(OOD) intents is essential for developing new skills in a task-oriented dialogue system. The key challenge is how to transfer prior IND knowledge to OOD clustering. Different from existing work b…

ClusteringContrastive LearningIntent DiscoveryTransfer Learning

Self-Supervised Interest Transfer Network via Prototypical Contrastive Learning for Recommendation

2023-02-28 · Guoqiang Sun, Yibin Shen, Sijin Zhou, Xiang Chen 외

Cross-domain recommendation has attracted increasing attention from industry and academia recently. However, most existing methods do not exploit the interest invariance between domains, which would yield sub-optimal sol…

Contrastive Learning