Community Detection in Attributed Networks Via Adaptive Deep Nonnegative Matrix Factorization
NEURAL COMPUTING & APPLICATIONS(2023)
South China Normal University
Abstract
Community detection plays an important role in analyzing attributed networks. It attempts to find the optimal cluster structures to identify valuable information. Although deep nonnegative matrix factorization (DNMF) is widely used in community detection, it cannot be used to analyze attributed networks since only topology information is considered. Recent researches have taken attribute information into account, but we still need to face the following challenges. First, it is difficult to deal with topology noise and attribute noise in attributed networks at one stroke. Second, we need to balance the coupling between topology and node attributes with hyperparameters in most methods. However, with inappropriate hyperparameters, it is easy to cause interference and compromise between them. For the above challenges, in this paper, we propose a novel method, namely adaptive deep nonnegative matrix factorization. Specifically, we handle the inherent noise of attributed networks via dual-DNMF with autoencoder. And then, we use the attention mechanism to adaptively integrate topology information and attribute information without adjusting hyperparameters manually. Overall, our method not only handles the inherent noise in attributed networks, but also resolves the interference and compromise between topology and attributes in a generalized way. The results of comprehensive experiments support our conclusions and demonstrate that our method outperforms the state-of-the-art methods in most datasets.
MoreTranslated text
Key words
Deep nonnegative matrix factorization,Community detection,Attention mechanism,Attributed networks,Autoencoder
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example

Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined