paper-with-me

Papers

Cross-domain Network Representations

2019-08-01 · Shan Xue, Jie Lu, Guangquan Zhang

The purpose of network representation is to learn a set of latent features by obtaining community information from network structures to provide knowledge for machine learning tasks. Recent research has driven significant progress in network representation by employing random walks as the network sampling strategy. Nevertheless, existing approaches rely on domain-specifically rich community structures and fail in the network that lack topological information in its own domain. In this paper, we propose a novel algorithm for cross-domain network representation, named as CDNR. By generating the random walks from a structural rich domain and transferring the knowledge on the random walks across domains, it enables a network representation for the structural scarce domain as well. To be specific, CDNR is realized by a cross-domain two-layer node-scale balance algorithm and a cross-domain two-layer knowledge transfer algorithm in the framework of cross-domain two-layer random walk learning. Experiments on various real-world datasets demonstrate the effectiveness of CDNR for universal networks in an unsupervised way.

📄 PDF Abstract BibTeX arXiv:1908.00205

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Transferability of Representations Learned using Supervised Contrastive Learning Trained on a Multi-Domain Dataset

2023-09-27 · Alvin De Jun Tan, Clement Tan, Chai Kiat Yeo

Contrastive learning has shown to learn better quality representations than models trained using cross-entropy loss. They also transfer better to downstream datasets from different domains. However, little work has been …

Contrastive LearningLinear evaluation

Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck

2022-03-31 · Jiangxia Cao, Jiawei Sheng, Xin Cong, Tingwen Liu 외

Recommender systems have been widely deployed in many real-world applications, but usually suffer from the long-standing user cold-start problem. As a promising way, Cross-Domain Recommendation (CDR) has attracted a surg…

Recommendation Systems

Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations

2022-04-06 · Jeff Z. HaoChen, Colin Wei, Ananya Kumar, Tengyu Ma

Contrastive learning is a highly effective method for learning representations from unlabeled data. Recent works show that contrastive representations can transfer across domains, leading to simple state-of-the-art algor…

Contrastive LearningDomain AdaptationUnsupervised Domain Adaptation

Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification

2019-08-24 · IJCNLP 2019 11 · Mengting Hu, Yike Wu, Shiwan Zhao, Honglei Guo 외

Cross-domain sentiment classification has drawn much attention in recent years. Most existing approaches focus on learning domain-invariant representations in both the source and target domains, while few of them pay att…

ClassificationGeneral ClassificationSentiment AnalysisSentiment Classification

Hierarchical Attention Fusion of Visual and Textual Representations for Cross-Domain Sequential Recommendation

2025-04-21 · Wangyu Wu, Zhenhong Chen, Siqi Song, Xianglin Qiua 외

Cross-Domain Sequential Recommendation (CDSR) predicts user behavior by leveraging historical interactions across multiple domains, focusing on modeling cross-domain preferences through intra- and inter-sequence item rel…

Decision MakingSequential Decision MakingSequential Recommendation