Filters








199 Hits in 4.2 sec

Neural Topic Modeling with Bidirectional Adversarial Training [article]

Rui Wang, Xuemeng Hu, Deyu Zhou, Yulan He, Yuxuan Xiong, Chenchen Ye, Haiyang Xu
2020 arXiv   pre-print
for neural topic modeling.  ...  To address these limitations, we propose a neural topic modeling approach, called Bidirectional Adversarial Topic (BAT) model, which represents the first attempt of applying bidirectional adversarial training  ...  Recently, the Adversarial-neural Topic Model (ATM) (Wang et al., 2019a) is proposed based on adversarial training, it models topics with Dirichlet prior which is able to capture the multi-modality compared  ... 
arXiv:2004.12331v1 fatcat:xsbtuzkfk5fvvmfm57ddt4izg4

Neural Topic Modeling with Cycle-Consistent Adversarial Training [article]

Xuemeng Hu, Rui Wang, Deyu Zhou, Yuxuan Xiong
2020 arXiv   pre-print
The recently proposed Adversarial-neural Topic Model models topics with an adversarially trained generator network and employs Dirichlet prior to capture the semantic patterns in latent topics.  ...  Advances on deep generative models have attracted significant research interest in neural topic modeling.  ...  To address such limitations of ATM, we propose a novel neural topic modeling approach, named Topic Modeling with Cycle-consistent Adversarial Training (ToMCAT).  ... 
arXiv:2009.13971v1 fatcat:humpi53tfbbprf3pq2pizek4nu

Neural Topic Modeling with Bidirectional Adversarial Training

Rui Wang, Xuemeng Hu, Deyu Zhou, Yulan He, Yuxuan Xiong, Chenchen Ye, Haiyang Xu
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
for neural topic modeling.  ...  To address these limitations, we propose a neural topic modeling approach, called Bidirectional Adversarial Topic (BAT) model, which represents the first attempt of applying bidirectional adversarial training  ...  Recently, the Adversarial-neural Topic Model (ATM) (Wang et al., 2019a) is proposed based on adversarial training, it models topics with Dirichlet prior which is able to capture the multi-modality compared  ... 
doi:10.18653/v1/2020.acl-main.32 fatcat:6rghvu477rdjddu6srnyum37zu

Neural Topic Modeling with Cycle-Consistent Adversarial Training

Xuemeng Hu, Rui Wang, Deyu Zhou, Yuxuan Xiong
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   unpublished
The recently proposed Adversarial-neural Topic Model models topics with an adversarially trained generator network and employs Dirichlet prior to capture the semantic patterns in latent topics.  ...  Advances on deep generative models have attracted significant research interest in neural topic modeling.  ...  incorporation of metadata. • ATM (Wang et al., 2019a) , a neural topic model utilizing adversarial training. • BAT (Wang et al., 2020) , a neural topic model utilizing bidirectional adversarial training  ... 
doi:10.18653/v1/2020.emnlp-main.725 fatcat:2qqtw7w26fbrdi2uasrt7jyyaa

ATM:Adversarial-neural Topic Model [article]

Rui Wang and Deyu Zhou and Yulan He
2019 arXiv   pre-print
To address these limitations, we propose a topic modeling approach based on Generative Adversarial Nets (GANs), called Adversarial-neural Topic Model (ATM).  ...  To illustrate the feasibility of porting ATM to tasks other than topic modeling, we apply ATM for open domain event extraction.  ...  Adversarial-neural Topic Model We propose the Advesarial-neural Topic Model (ATM) as shown in Figure 1 .  ... 
arXiv:1811.00265v2 fatcat:ydx5bt3pxvcobmv5uhrkflrx2u

Contrastive Learning for Neural Topic Model [article]

Thong Nguyen, Anh Tuan Luu
2021 arXiv   pre-print
Recent empirical studies show that adversarial topic models (ATM) can successfully capture semantic patterns of the document by differentiating a document with another dissimilar sample.  ...  topic model.  ...  To cope with this issue, Adversarial Topic Model (ATM) [10] [11] [12] [13] was proposed with adversarial mechanisms using a combination of generator and discriminator.  ... 
arXiv:2110.12764v1 fatcat:2oz4s2hfnvdjbpne6inqclpufa

DehazeGAN: When Image Dehazing Meets Differential Programming

Hongyuan Zhu, Xi Peng, Vijay Chandrasekhar, Liyuan Li, Joo-Hwee Lim
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Single image dehazing has been a classic topic in computer vision for years.  ...  Inspired by differentiable programming, we re-formulate the atmospheric scattering model into a novel generative adversarial network (DehazeGAN).  ...  by a neural network, and the model is further optimized in a data-driven way.  ... 
doi:10.24963/ijcai.2018/172 dblp:conf/ijcai/ZhuPCLL18 fatcat:uzy7eblnefcghkfhwgqzru7vjq

Adversarial Learning of Poisson Factorisation Model for Gauging Brand Sentiment in User Reviews [article]

Runcong Zhao and Lin Gui and Gabriele Pergola and Yulan He
2021 arXiv   pre-print
Different from existing models for sentiment-topic extraction which assume topics are grouped under discrete sentiment categories such as 'positive', 'negative' and 'neural', BTM is able to automatically  ...  BTM is built on the Poisson factorisation model with the incorporation of adversarial learning. It has been evaluated on a dataset constructed from Amazon reviews.  ...  In particular, Wang et al. (2019) has proposed an Adversarial-neural Topic Model (ATM) based on the Generative Adversarial Network (GAN) (Goodfellow et al., 2014) , that employees an adversarial approach  ... 
arXiv:2101.10150v1 fatcat:hyxyreo5cnenvnwczqil57tqgm

Neural Topic Modeling with Deep Mutual Information Estimation [article]

Kang Xu and Xiaoqiu Lu and Yuan-fang Li and Tongtong Wu and Guilin Qi and Ning Ye and Dong Wang and Zheng Zhou
2022 arXiv   pre-print
The emerging neural topic models make topic modeling more easily adaptable and extendable in unsupervised text mining.  ...  In this paper, we propose a neural topic model which incorporates deep mutual information estimation, i.e., Neural Topic Modeling with Deep Mutual Information Estimation(NTM-DMIE).  ...  Wang et al [12] propose the Adversarial neural Topic Model (ATM) that is based on adversarial training.  ... 
arXiv:2203.06298v1 fatcat:vls2jisyzjgbhhy2ws77yfuti4

Neural Topic Modeling by Incorporating Document Relationship Graph [article]

Deyu Zhou, Xuemeng Hu, Rui Wang
2020 arXiv   pre-print
In this paper, we propose Graph Topic Model (GTM), a GNN based neural topic model that represents a corpus as a document relationship graph.  ...  Graph Neural Networks (GNNs) that capture the relationships between graph nodes via message passing have been a hot research direction in the natural language processing community.  ...  ) , while adversarial topic model (Wang et al., 2019a (Wang et al., ,b, 2020 directly generates documents from the Dirichlet prior and such a process is adversarially trained with a discriminator under  ... 
arXiv:2009.13972v1 fatcat:7downew5wbhabgetrmggwonxo4

Variational Gaussian Topic Model with Invertible Neural Projections [article]

Rui Wang, Deyu Zhou, Yuxuan Xiong, Haiping Huang
2021 arXiv   pre-print
Neural topic models have triggered a surge of interest in extracting topics from text automatically since they avoid the sophisticated derivations in conventional topic models.  ...  However, scarce neural topic models incorporate the word relatedness information captured in word embedding into the modeling process.  ...  Dieng et al., 2019), is a neural topic model on embedding space, we use the original implementation 8 . • ATM (Wang et al., 2019) , is a neural topic modeling approach based on adversarial training, we  ... 
arXiv:2105.10095v1 fatcat:wurjck5rznhdzjtor6ee3tjfr4

Survey of Various Techniques used for Credit Card Fraud Detection

Aayushi Agarwal
2020 International Journal for Research in Applied Science and Engineering Technology  
Government is making attempt to make India a digital country, So using an ATM or credit card is a convenient way of fulfilling the government's aim.  ...  Mary Frances Zeager et.al Adversarial Learning Adversarial framework outperforms other static models. Table i : i Comparison of Techniques  ...  If you are not feeling comfortable inside the ATM then cancel the transaction and use some other ATM. b) If there is any unusual activity in the ATM or if there is any chances of damaged ATM then it's  ... 
doi:10.22214/ijraset.2020.30614 fatcat:epycrw76sjhnnatrrkxvn7th4m

Adversarial Examples: Attacks and Defenses for Deep Learning

Xiaoyong Yuan, Pan He, Qile Zhu, Xiaolin Li
2019 IEEE Transactions on Neural Networks and Learning Systems  
However, deep neural networks (DNNs) have been recently found vulnerable to well-designed input samples called adversarial examples.  ...  Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples.  ...  ., training data poisoning) is another interesting topic and has been studied in [38] - [43] . Due to the limitation of space, we do not include this topic in the paper.  ... 
doi:10.1109/tnnls.2018.2886017 pmid:30640631 fatcat:enznysw3svfzdjrmubwkedr6me

Adversarial Examples: Attacks and Defenses for Deep Learning [article]

Xiaoyong Yuan, Pan He, Qile Zhu, Xiaolin Li
2018 arXiv   pre-print
Adversarial examples are imperceptible to human but can easily fool deep neural networks in the testing/deploying stage.  ...  However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples.  ...  Due to the limitation of space, we do not include this topic in the paper. • Since the great performance achieved by deep learning, we only study the attacks against deep neural networkbased models.  ... 
arXiv:1712.07107v3 fatcat:5wcz4h4eijdsdjeqwdpzbfbjeu

Adapting Text Embeddings for Causal Inference [article]

Victor Veitch and Dhanya Sridhar and David M. Blei
2020 arXiv   pre-print
Our method adapts language models (specifically, word embeddings and topic models) to learn document embeddings that are able to predict both treatment and outcome.  ...  The second is efficient language modeling: representations of text are designed to dispose of linguistically irrelevant information, and this information is also causally irrelevant.  ...  We refer to this model as the causal amortized topic model (Causal ATM). Validity.  ... 
arXiv:1905.12741v2 fatcat:edj7kasahfcsrajgjkyamugvn4
« Previous Showing results 1 — 15 out of 199 results