
Network Together: Node Classification via CrossNetwork Deep Network Embedding
Network embedding is a highly effective method to learn lowdimensional ...
read it

Network Transfer Learning via Adversarial Domain Adaptation with Graph Convolution
This paper studies the problem of crossnetwork node classification to o...
read it

Deep Adversarial Transition Learning using CrossGrafted Generative Stacks
Current deep domain adaptation methods used in computer vision have main...
read it

Deep Network Embedding for Graph Representation Learning in Signed Networks
Network embedding has attracted an increasing attention over the past fe...
read it

DAHGT: Domain Adaptive Heterogeneous Graph Transformer
Domain adaptation using graph networks is to learn labeldiscriminative ...
read it

Deep Node Ranking: an Algorithm for Structural Network Embedding and EndtoEnd Classification
Complex networks are used as an abstraction for systems modeling in phys...
read it

Flexible Attributed Network Embedding
Network embedding aims to find a way to encode network by learning an em...
read it
Adversarial Deep Network Embedding for Crossnetwork Node Classification
In this paper, the task of crossnetwork node classification, which leverages the abundant labeled nodes from a source network to help classify unlabeled nodes in a target network, is studied. The existing domain adaptation algorithms generally fail to model the network structural information, and the current network embedding models mainly focus on singlenetwork applications. Thus, both of them cannot be directly applied to solve the crossnetwork node classification problem. This motivates us to propose an adversarial crossnetwork deep network embedding (ACDNE) model to integrate adversarial domain adaptation with deep network embedding so as to learn networkinvariant node representations that can also well preserve the network structural information. In ACDNE, the deep network embedding module utilizes two feature extractors to jointly preserve attributed affinity and topological proximities between nodes. In addition, a node classifier is incorporated to make node representations labeldiscriminative. Moreover, an adversarial domain adaptation technique is employed to make node representations networkinvariant. Extensive experimental results demonstrate that the proposed ACDNE model achieves the stateoftheart performance in crossnetwork node classification.
READ FULL TEXT
Comments
There are no comments yet.