返回
Relation-Guided Representation Learning
DOI:10.1016/j.neunet.2020.07.014.png)
摘要
En 中文
Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data from a latent space and neglect rich latent structural information. In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning. Different from previous work, our framework well preserves the relations between samples. Since the prediction of pairwise relations themselves is a fundamental problem, our model adaptively learns them from data. This provides much flexibility to encode real data manifold. The important role of relation and representation learning is evaluated on the clustering task. Extensive experiments on benchmark data sets demonstrate the superiority of our approach. By seeking to embed samples into subspace, we further show that our method can address the large-scale and out-of-sample problem. Our source code is publicly available at: https://github.com/nbShawnLu/RGRL. (C) 2020 Elsevier Ltd. All rights reserved.
Keyword:
Deep auto-encoder
Unsupervised representation learning
Subspace clustering
Pairwise relation
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
7.8K
被引数:
3.0W
机构
引用论文
Evaluating the Interpersonal Needs Questionnaire: Comparison of the Reliability, Factor Structure, and Predictive Validity across Five Versions评估人际需求问卷: 五个版本的可靠性,因素结构和预测效度的比较
Unsupervised feature selection via latent representation learning and manifold regularization
NEURAL NETWORKS
IF6.3
Taurine modulation of hypochlorous acid-induced lung epithelial cell injury in vitro. Role of anion transport.牛磺酸对次氯酸诱导的体外肺上皮细胞损伤的调节作用。阴离子运输的作用。

