Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning

نویسندگان

چکیده

Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful labeled data remaining massive unlabeled via graph. As one most popular graph-based SSL approaches, recently proposed Graph Convolutional Networks (GCNs) have gained remarkable progress by combining sound expressiveness neural networks with graph structure. Nevertheless, existing methods do not directly address core problem SSL, \emph{i.e.}, shortage supervision, and thus their performances are still very limited. To accommodate this issue, paper presents novel GCN-based algorithm which enrich supervision signals utilizing both similarities Firstly, designing semi-supervised contrastive loss, improved node representations can be generated maximizing agreement between different views same or from class. Therefore, rich scarce yet valuable jointly provide abundant information for learning discriminative representations, helps improve subsequent classification result. Secondly, underlying determinative relationship input topology features is extracted as supplementary using generative loss related features. Intensive experimental results on variety real-world datasets firmly verify effectiveness our when compared other state-of-the-art methods.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semisupervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local vertex features and graph topology in the convolutional layers. Although the GCN model compares favorably with other state-of-the-art methods, its mechanisms ar...

متن کامل

Semi-Supervised Classification with Graph Convolutional Networks

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden lay...

متن کامل

Graph-Based Semi-Supervised Learning as a Generative Model

This paper proposes and develops a new graph-based semi-supervised learning method. Different from previous graph-based methods that are based on discriminative models, our method is essentially a generative model in that the class conditional probabilities are estimated by graph propagation and the class priors are estimated by linear regression. Experimental results on various datasets show t...

متن کامل

Graph-Based Semi-Supervised Learning

While labeled data is expensive to prepare, ever increasing amounts of unlabeled data is becoming widely available. In order to adapt to this phenomenon, several semi-supervised learning (SSL) algorithms, which learn from labeled as well as unlabeled data, have been developed. In a separate line of work, researchers have started to realize that graphs provide a natural way to represent data in ...

متن کامل

Graph-based semi-supervised learning for relational networks

We address the problem of semi-supervised learning in relational networks, networks in which nodes are entities and links are the relationships or interactions between them. Typically this problem is confounded with the problem of graph-based semi-supervised learning (GSSL), because both problems represent the data as a graph and predict the missing class labels of nodes. However, not all graph...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence

سال: 2021

ISSN: ['2159-5399', '2374-3468']

DOI: https://doi.org/10.1609/aaai.v35i11.17206