Filters








33,172 Hits in 3.8 sec

An Adversarial Transfer Network for Knowledge Representation Learning [article]

Huijuan Wang, Shuangyin Li, Rong Pan
2021 pre-print
We propose an adversarial embedding transfer network ATransN, which transfers knowledge from one or more teacher knowledge graphs to a target one through an aligned entity set without explicit data leakage  ...  The extension of combining other knowledge graph embedding algorithms and the extension with three teacher graphs display the promising generalization of the adversarial transfer network.  ...  ADVERSARIAL TRANSFER NETWORK Given entity embeddings of a teacher knowledge graph and a target knowledge graph, the goal of the Adversarial Transfer Network is to learn the entity and relation embeddings  ... 
doi:10.1145/3442381.3450064 arXiv:2104.14757v1 fatcat:yticwfcvozgapfejfek62qkud4

KTAN: Knowledge Transfer Adversarial Network [article]

Peiye Liu, Wu Liu, Huadong Ma, Tao Mei, Mingoo Seok
2018 arXiv   pre-print
In this paper, we propose a knowledge transfer adversarial network to better train a student network.  ...  Furthermore, we infuse an adversarial learning process by employing a discriminator network, which can fully exploit the spatial correlation of feature maps in training a student network.  ...  knowledge to a student network in an adversarial learning manner; • Extensive experiments conducted on both image classification and object detection tasks verify the merit of our knowledge transfer adversarial  ... 
arXiv:1810.08126v1 fatcat:arj5al4cevfmdhqdptkfgcvhh4

Domain Adaptation for Reinforcement Learning on the Atari [article]

Thomas Carr, Maria Chli, George Vogiatzis
2018 arXiv   pre-print
Our work presents an algorithm for initialising the hidden feature representation of the target task.  ...  We utilise adversarial domain adaptation ideas combined with an adversarial autoencoder architecture.  ...  Conclusion We have presented an adversarial method for knowledge transfer in reinforcement learning.  ... 
arXiv:1812.07452v1 fatcat:mdhunianpjdvbn2u6nmqrxn7ta

A Survey on Deep Transfer Learning [article]

Chuanqi Tan, Fuchun Sun, Tao Kong, Wenchang Zhang, Chao Yang and Chunfang Liu
2018 arXiv   pre-print
This survey focuses on reviewing the current researches of transfer learning by using deep neural network and its applications.  ...  We defined deep transfer learning, category and review the recent research works based on the techniques used in deep transfer learning.  ...  Adversarial-based deep transfer learning Adversarial-based deep transfer learning refers to introduce adversarial technology inspired by generative adversarial nets (GAN) [7] to find transferable representations  ... 
arXiv:1808.01974v1 fatcat:pdkq4uskazhslopclb5zhmeigi

Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution [article]

Quanyu Dai, Xiao-Ming Wu, Jiaren Xiao, Xiao Shen, Dan Wang
2022 arXiv   pre-print
It consists of two components: a semi-supervised learning component and an adversarial domain adaptation component.  ...  between the source and target domains to facilitate knowledge transfer.  ...  effectiveness for knowledge transfer across networks.  ... 
arXiv:1909.01541v4 fatcat:43rwyp3v3vel3jnho3oyyqaicu

MHTN: Modal-Adversarial Hybrid Transfer Network for Cross-Modal Retrieval

Xin Huang, Yuxin Peng, Mingkuan Yuan
2018 IEEE Transactions on Cybernetics  
Second, a modal-adversarial semantic learning subnetwork is proposed to construct an adversarial training mechanism between the common representation generator and modality discriminator, making the common  ...  , which distills modal-independent supplementary knowledge for promoting cross-modal common representation learning.  ...  Our MHTN is an end-to-end architecture with modalsharing knowledge transfer subnetwork and modal-adversarial semantic learning subnetwork.  ... 
doi:10.1109/tcyb.2018.2879846 pmid:30530383 fatcat:2zstuyrwobcm7iemoolebknexe

MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval [article]

Xin Huang, Yuxin Peng, Mingkuan Yuan
2017 arXiv   pre-print
to all modalities in target domain with a star network structure, which distills modal-independent supplementary knowledge for promoting cross-modal common representation learning. (2) Modal-adversarial  ...  semantic learning subnetwork is proposed to construct an adversarial training mechanism between common representation generator and modality discriminator, making the common representation discriminative  ...  Our MHTN is an end-to-end architecture with modalsharing knowledge transfer subnetwork and modal-adversarial semantic learning subnetwork.  ... 
arXiv:1708.04308v1 fatcat:6ilastoaonddtn7vtxr4g3noga

Hierarchical Knowledge Squeezed Adversarial Network Compression

Peng Li, Chang Shu, Yuan Xie, Yan Qu, Hui Kong
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
adversarial training framework to learn the student network.  ...  Recently, more focuses have been transferred to employ the adversarial training to minimize the discrepancy between distributions of output from two networks.  ...  For fair comparison, we adopt their representation of transferred knowledge into our framework.  ... 
doi:10.1609/aaai.v34i07.6799 fatcat:cht7mlfwrnebbivrufrc4zpp5u

Deep Transfer Learning for EEG-based Brain Computer Interface [article]

Chuanqi Tan, Fuchun Sun, Wenchang Zhang
2018 arXiv   pre-print
Second, we design a deep transfer learning framework which is suitable for transferring knowledge by joint training, which contains a adversarial network and a special loss function.  ...  Herein, we propose a novel deep transfer learning approach to solve these two problems.  ...  Second, we designed a deep transfer learning framework suitable for transferring knowledge by joint training, which contains an adversarial network and a special loss function.  ... 
arXiv:1808.01752v1 fatcat:vlcxkl3wyjggpghoxgeau7rqbe

A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks [article]

Jacob M. Springer, Melanie Mitchell, Garrett T. Kenyon
2021 arXiv   pre-print
Adversarial examples for neural network image classifiers are known to be transferable: examples optimized to be misclassified by a source classifier are often misclassified as well by classifiers with  ...  representation-targeted adversarial attacks, even between architectures as different as convolutional neural networks and transformers.  ...  Acknowledgments and Disclosure of Funding The authors would like to thank Rory Soiffer, Juston Moore, and Hadyn Jones for their helpful discussions and comments.  ... 
arXiv:2106.02105v2 fatcat:gjgkossynncw7k6iexown7rlpq

PrivNet: Safeguarding Private Attributes in Transfer Learning for Recommendation [article]

Guangneng Hu, Qiang Yang
2020 arXiv   pre-print
The key idea is to simulate the attacks during the training for protecting unseen users' privacy in the future, modeled by an adversarial game, so that the transfer learning model becomes robust to attacks  ...  Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain.  ...  Yu Zhang for insightful discussion. We thank the new publication paradigm, i.e., "Findings of ACL: EMNLP 2020", which makes this paper indexed in the ACL anthology.  ... 
arXiv:2010.08187v1 fatcat:pvqennwzmvf5jie6ts2fqqbif4

Learning Multi-Domain Adversarial Neural Networks for Text Classification

Xiao Ding, Qiankun Shi, Bibo Cai, Ting Liu, Yanyan Zhao, Qiang Ye
2019 IEEE Access  
Deep neural networks have been applied to learn transferable features for adapting text classification models from a source domain to a target domain.  ...  In this paper, we use an adversarial training strategy and orthogonality constraints to guarantee that the private and shared features do not collide with each other, which can improve the performances  ...  ACKNOWLEDGMENT The author would like to thank the anonymous reviewers for their constructive comments.  ... 
doi:10.1109/access.2019.2904858 fatcat:gxg7vmhmdbd7jbn7rptvovnzrq

VerifyTL: Secure and Verifiable Collaborative Transfer Learning [article]

Zhuoran Ma, Jianfeng Ma, Yinbin Miao, Ximeng Liu, Wei Zheng, Kim-Kwang Raymond Choo, Robert H. Deng
2020 arXiv   pre-print
Hence, one often resorts to transfer learning to transfer knowledge learned from a source domain with sufficient labelled data to a target domain with limited labelled data.  ...  In this paper we construct a secure and Verifiable collaborative Transfer Learning scheme, VerifyTL, to support two-way transfer learning over potentially untrusted datasets by improving knowledge transfer  ...  In addition, the transferred knowledge may be revealed, for example by successfully carrying out an inference attack over the data representations to reconstruct the training data [6] , [8] .  ... 
arXiv:2005.08997v1 fatcat:2a4soioeujagdjh5lc74mcs7vy

A Survey of Adversarial Machine Learning in Cyber Warfare

Vasisht Duddu
2018 Defence Science Journal  
We explore the threat models for Machine Learning systems and describe the various techniques to attack and defend them.  ...  Adversarial machine learning is a fast growing area of research which studies the design of Machine Learning algorithms that are robust in adversarial environments.  ...  They design an attack on the internal latent representations to make the adversarial input produce an internal representation similar to the target's representation. Makhzani 44 , et al.  ... 
doi:10.14429/dsj.68.12371 fatcat:vyupcxe6hrhllb4rowequxrf5i

Knowledge Squeezed Adversarial Network Compression [article]

Shu Changyong and Li Peng and Xie Yuan and Qu Yanyun and Dai Longquan and Ma Lizhuang
2019 arXiv   pre-print
, under the adversarial training framework to learn the student network.  ...  Then, the transferred knowledge from teacher network could accommodate the size of student network.  ...  For fair comparison, we adopt their representation of transferred knowledge into our framework.  ... 
arXiv:1904.05100v2 fatcat:m6tbpwkgivf6pj4kozrkh2lzwy
« Previous Showing results 1 — 15 out of 33,172 results