6,140 Hits in 5.6 sec

Cross Domain Regularization for Neural Ranking Models Using Adversarial Learning [article]

Daniel Cohen, Bhaskar Mitra, Katja Hofmann, W. Bruce Croft
2018 arXiv   pre-print
We use an adversarial discriminator and train our neural ranking model on a small set of domains.  ...  We study the effectiveness of adversarial learning as a cross domain regularizer in the context of the ranking task.  ...  CROSS DOMAIN REGULARIZATION USING ADVERSARIAL LEARNING The motivation of the adversarial discriminator is to force the neural model to learn domain independent features that are useful to estimate relevance  ... 
arXiv:1805.03403v1 fatcat:sl2tum3325etdjtroyigsqg6xy

Learning Shared Semantic Space with Correlation Alignment for Cross-modal Event Retrieval [article]

Zhenguo Yang, Zehang Lin, Peipei Kang, Jianming Lv, Qing Li, Wenyin Liu
2019 arXiv   pre-print
deep neural networks designed for heterogeneous data.  ...  In the context of cross-modal (event) retrieval, we design a neural network with convolutional layers and fully-connected layers to extract features for images, including images on Flickr-like social media  ...  neural networks trained on images and texts. We contribute a weakly-aligned unpaired Wiki-Flickr Event dataset as a complement of the existing paired datasets for cross-modal retrieval.  ... 
arXiv:1901.04268v3 fatcat:hipjb7ba2fg3hp5g5d3oq3kaki

kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification [article]

Jiaxiang Liu, Xuyi Chen, Shikun Feng, Shuohuan Wang, Xuan Ouyang, Yu Sun, Zhengjie Huang, Weiyue Su
2020 arXiv   pre-print
Furthermore, the adversarial training with a multi-lingual model is used to achieve 1st place of SemEval-2020 Task 9 Hindi-English sentiment classification competition.  ...  In this work, the domain transfer learning from state-of-the-art uni-language model ERNIE is tested on the code-mixing dataset, and surprisingly, a strong baseline is achieved.  ...  ., 2019) which uses the paradigm of continuous learning to pretrain language models which are adapted to sentiment classification using domain transfer learning.  ... 
arXiv:2009.03673v2 fatcat:nvt6qknb7vag5itmtibgnvle6y

Guest Editorial: Special Issue on Deep Representation and Transfer Learning for Smart and Connected Health

Vasile Palade, Stefan Wermter, Ariel Ruiz-Garcia, Antonio De Padua Braga, Clive Cheong Took
2021 IEEE Transactions on Neural Networks and Learning Systems  
In the article "Task similarity estimation through adversarial multitask neural network," Zhou et al. provide a theoretical perspective of the advantages of using information similarity for multitask learning  ...  Their approach uses adversarial training to learn task dependencies through multitask learning networks.  ... 
doi:10.1109/tnnls.2021.3049931 fatcat:g2kdub6kmnep5o3rx3sqiacexm

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [article]

Yang Wang
2020 arXiv   pre-print
Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces.  ...  Recently, deep neural networks have exhibited as a powerful architecture to well capture the nonlinear distribution of high-dimensional multimedia data, so naturally does for multi-modal data.  ...  Du et al [25] constructed a multi-view adversarially learned inference model, named MALI, to achieve cross-domain joint proposed the adversarially learned inference (ALI) model, which jointly learned  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

WUT at SemEval-2019 Task 9: Domain-Adversarial Neural Networks for Domain Adaptation in Suggestion Mining

Mateusz Klimaszewski, Piotr Andruszkiewicz
2019 Proceedings of the 13th International Workshop on Semantic Evaluation  
Preserving Domain-Adversarial Neural Networks.  ...  We present a system for cross-domain suggestion mining, prepared for the SemEval-2019 Task 9: Suggestion Mining from Online Reviews and Forums (Subtask B).  ...  Conclusion In this work, we introduced a new system for cross-domain suggestion mining based on the domain-adversarial neural networks.  ... 
doi:10.18653/v1/s19-2221 dblp:conf/semeval/KlimaszewskiA19 fatcat:fh7od3hvjvcsnmzway3ekhabdy

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 2702-2713 Image Recovery via Transform Learning and Low-Rank Modeling: The Power of Complementary Regularizers.  ...  ., +, TIP 2020 525-537 Improved Techniques for Adversarial Discriminative Domain Adaptation.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Semi-supervised adversarial neural networks for single-cell classification

Jacob C Kimmel, David R Kelley
2021 Genome Research  
Here, we present scNym, a semi-supervised, adversarial neural network that learns to transfer cell identity annotations from one experiment to another. scNym takes advantage of information in both labeled  ...  In addition to high performance, we show that scNym models are well-calibrated and interpretable with saliency methods.  ...  Singh, and Han Yuan for helpful discussions and comments. Funding for this study was provided by Calico Life Sciences, LLC.  ... 
doi:10.1101/gr.268581.120 pmid:33627475 pmcid:PMC8494222 fatcat:o22a5tajd5aitgcrs3zxgndlty

Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-Identification

Guangcong Wang, Jian-Huang Lai, Wenqi Liang, Guangrun Wang
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To reduce the gap between the source and target domains, we propose a Smoothing Adversarial Domain Attack (SADA) approach that guides the source domain images to align the target domain images by using  ...  With both SADA and pMR, the proposed method significantly improves the cross-domain person re-ID.  ...  For example, [6] proposed to directly use a cycle generative adversarial model to reduce the domain gap problem.  ... 
doi:10.1109/cvpr42600.2020.01058 dblp:conf/cvpr/WangLLW20 fatcat:z37bb6thefgkrfbrsapsyzbjfu

Adversarial Personalized Ranking for Recommendation

Xiangnan He, Zhankui He, Xiaoyu Du, Tat-Seng Chua
2018 The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval - SIGIR '18  
Using matrix Factorization (MF) --- the most widely used model in recommendation --- as a demonstration, we show that optimizing it with BPR leads to a recommender model that is not robust.  ...  Item recommendation is a personalized ranking task. To this end, many recommender systems optimize models with pairwise ranking objectives, such as the Bayesian Personalized Ranking (BPR).  ...  Neural Factorization Machine [16] and Deep Crossing [29] .  ... 
doi:10.1145/3209978.3209981 dblp:conf/sigir/0001HDC18 fatcat:5ccueqim7fgylh2td52ozszip4

From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems [article]

Yao Zhou, Haonan Wang, Jingrui He, Haixun Wang
2021 arXiv   pre-print
Each strategy explains its ranking decisions via different mechanisms: attention weights, adversarial perturbations, and counterfactual perturbations.  ...  However, many of them remain difficult to diagnose what aspects of the deep models' input drive the final ranking decision, thus, they cannot often be understood by human stakeholders.  ...  Adversarial augmentation network. Considering that we aim to use adversarial perturbation for generating the explainable perturbations, the first step is to learn the base recommendation model 2 .  ... 
arXiv:2110.14844v1 fatcat:e3s7nbxivzhknidbckjek2hx2e

Transfer Adaptation Learning: A Decade Survey [article]

Lei Zhang, Xinbo Gao
2020 arXiv   pre-print
TAL aims to build models that can perform tasks of target domain by learning knowledge from a semantic related but distribution different source domain.  ...  Conventional machine learning aims to find a model with the minimum expected risk on test data by minimizing the regularized empirical risk on the training data, which, however, supposes that the training  ...  ACKNOWLEDGMENT The author would like to thank the pioneer researchers in transfer learning, domain adaptation and other related fields. The author would also like to thank Dr. Mingsheng Long and Dr.  ... 
arXiv:1903.04687v2 fatcat:wurprqieffalnnp6isfkhh5y5i

An Introduction to Person Re-identification with Generative Adversarial Networks [article]

Hamed Alqahtani, Manolya Kavakli-Thorne, Charles Z. Liu
2019 arXiv   pre-print
Generative Adversarial Nets (GANs) in the past few years attracted lots of attention in solving these problems.  ...  Fortunately, deep learning paradigm opens new ways of the person re-identification research and becomes a hot spot in this field.  ...  These methods employed different neural network models like conventional neural network generative adversarial network and recurrent neural network for addressing the problem of person reidentification  ... 
arXiv:1904.05992v2 fatcat:iblztnj6efcgjdvudeuwqvbl54

2021 Index IEEE Transactions on Computational Imaging Vol. 7

2021 IEEE Transactions on Computational Imaging  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TCI 2021 724-733 Graph neural networks Graph Convolutional Networks for Model-Based Learning in Nonlinear Inverse Problems.  ...  ., +, TCI 2021 1161-1175 + Check author entry for coauthors serving Cross Network. Tang, W., +, TCI 2021 584-597 Hyperspectral Imagery Spatial Super-Resolution Using Generative Adversarial Network.  ... 
doi:10.1109/tci.2022.3151176 fatcat:slyirmc7c5egfjjjyfswassh24

A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks [article]

Yashar Deldjoo and Tommaso Di Noia and Felice Antonio Merra
2020 arXiv   pre-print
The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another  ...  This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality.  ...  Cross-domain Recommendation Recommender models are usually designed to compute recommendations for items belonging to a single domain.  ... 
arXiv:2005.10322v2 fatcat:4wqcluqgnbbwpkicunn42et5te
« Previous Showing results 1 — 15 out of 6,140 results