Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure
نویسندگان
چکیده
منابع مشابه
Regularizing graph centrality computations
Centrality metrics such as betweenness and closeness have been used to identify important nodes in a network. However, it takes days to months on a high-end workstation to compute the centrality of today’s networks. The main reasons are the size and the irregular structure of these networks. While today’s computing units excel at processing dense and regular data, their performance is questiona...
متن کاملAutomatic Service Composition Based on Graph Coloring
Web services as independent software components are published on the Internet by service providers and services are then called by users’ request. However, in many cases, no service alone can be found in the service repository that could satisfy the applicant satisfaction. Service composition provides new components by using an interactive model to accelerate the programs. Prior to service comp...
متن کاملAutomatic Service Composition Based on Graph Coloring
Web services as independent software components are published on the Internet by service providers and services are then called by users’ request. However, in many cases, no service alone can be found in the service repository that could satisfy the applicant satisfaction. Service composition provides new components by using an interactive model to accelerate the programs. Prior to service comp...
متن کاملVariance Regularizing Adversarial Learning
We introduce a novel approach for training adversarial models by replacing the discriminator score with a bi-modal Gaussian distribution over the real/fake indicator variables. In order to do this, we train the Gaussian classifier to match the target bi-modal distribution implicitly through meta-adversarial training. We hypothesize that this approach ensures a nonzero gradient to the generator,...
متن کاملRegularizing deep networks using efficient layerwise adversarial training
Adversarial training has been shown to regularize deep neural networks in addition to increasing their robustness to adversarial examples. However, its impact on very deep state of the art networks has not been fully investigated. In this paper, we present an efficient approach to perform adversarial training by perturbing intermediate layer activations and study the use of such perturbations a...
متن کاملذخیره 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: IEEE Transactions on Knowledge and Data Engineering
سال: 2021
ISSN: 1041-4347,1558-2191,2326-3865
DOI: 10.1109/tkde.2019.2957786