Filters








53 Hits in 5.2 sec

Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation [article]

Yong-Hui Liu, Chuan-Xian Ren, Xiao-Lin Xu, Ke-Kun Huang
2022 arXiv   pre-print
unlabeled target domain.  ...  It also avoids the cross-validation procedure to determine the margin parameter in traditional triplet loss based methods.  ...  Images for the Product domain are real article images from the e-commerce website, and images in the Real life domain are customer review images.  ... 
arXiv:2203.06836v1 fatcat:55z2fizqsveexcc6ids5ze7iem

From Intervention to Domain Transportation: A Novel Perspective to Optimize Recommendation [article]

Da Xu, Yuting Ye, Chuanwei Ruan
2022 arXiv   pre-print
The interventional nature of recommendation has attracted increasing attention in recent years.  ...  the target domain (distribution) of interest.  ...  Therefore, we alternatively consider optimizing recommendation as searching for an intervention that best transports the patterns it learns from the source domain to its intervention domain.  ... 
arXiv:2203.13956v1 fatcat:7in5hdfoebc5hjlspwrcjc7k6i

A Survey on Generative Adversarial Networks: Variants, Applications, and Training [article]

Abdul Jabbar, Xi Li, Bourahla Omar
2020 arXiv   pre-print
The Generative Models have gained considerable attention in the field of unsupervised learning via a new and practical framework called Generative Adversarial Networks (GAN) due to its outstanding data  ...  Therefore, stable training is a crucial issue in different applications for the success of GAN.  ...  automatic driving [236] , continual learning [237] , molecule development in oncology [238] , GANs for finance [239] [240] [241] [242] , GANs for textile [243, 244] , GANs for e-commerce [245] ,  ... 
arXiv:2006.05132v1 fatcat:gyjezuh5sfdilkp43ydsea5cwa

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
successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions.  ...  However, success has been accompanied with a major new arising challenge: many applications of machine learning (ML) are adversarial in nature.  ...  Second, users' interests and needs span across different application areas and large e-commerce sites, like Amazon or eBay, store users' preference scores related to products/services of various domains  ... 
arXiv:2005.10322v2 fatcat:4wqcluqgnbbwpkicunn42et5te

Transfer Adaptation Learning: A Decade Survey [article]

Lei Zhang, Xinbo Gao
2020 arXiv   pre-print
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  ...  The world we see is ever-changing and it always changes with people, things, and the environment. Domain is referred to as the state of the world at a certain moment.  ...  Lixin Duan for their kindly help in providing insightful discussions.  ... 
arXiv:1903.04687v2 fatcat:wurprqieffalnnp6isfkhh5y5i

Generalized Zero Shot Learning via Synthesis Pseudo Features

Chuanlong Li, Xiufen Ye, Haibo Yang, Yatong Han, Xiang Li, Yunpeng Jia
2019 IEEE Access  
For more information, see http://creativecommons.org/licenses/by/3.0/  ...  Such preservation can be beneficial for improving classification accuracy.  ...  TFGNSCS [25] also integrates a Wasserstein generative adversarial network with classification and transfer losses to generate sufficient convolutional neural network (CNN) features.  ... 
doi:10.1109/access.2019.2925093 fatcat:3fb5ymjmuzd43p55oguxndm42a

Deep Reinforcement Learning [article]

Yuxi Li
2018 arXiv   pre-print
Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn.  ...  We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources.  ...  The authors present an implementation with centralized training for decentralized execution, as discussed below. The authors experiment with grid world coordination, a partially observable game,  ... 
arXiv:1810.06339v1 fatcat:kp7atz5pdbeqta352e6b3nmuhy

Directions of the 100 most cited chatbot-related human behavior research: A review of academic publications

Jingyun Wang, Gwo-Haur Hwang, Ching-Yi Chang
2021 Computers and Education: Artificial Intelligence  
Increasing evidence has shown that chatbots have the potential to change the way people learn and search for information in human behavior.  ...  However, a systematic review of chatbot-related human behavior research with high citation rates has not been performed.  ...  and dual wasserstein generative adversarial networks 70 2019 Van den Broeck, E; Zarouali, B; Poels, K 2 Chatbot advertising effectiveness: when does the message get through?  ... 
doi:10.1016/j.caeai.2021.100023 fatcat:dbl3ncviwzbmpek7ojl4oxeyhm

Deep Learning for Free-Hand Sketch: A Survey [article]

Peng Xu, Timothy M. Hospedales, Qiyue Yin, Yi-Zhe Song, Tao Xiang, Liang Wang
2022 arXiv   pre-print
(iii) Promotion of future work via a discussion of bottlenecks, open problems, and potential research directions for the community.  ...  This is important in practice, e.g., for an e-commerce application of SBIR, where new products should ideally be enrolled in the search engine without requiring re-training.  ...  The arrow lengths denote the distances of cross-domain gap. See text for details.  ... 
arXiv:2001.02600v3 fatcat:lek5sivzsrat3i52lqh2eifnia

Artificial Intellgence – Application in Life Sciences and Beyond. The Upper Rhine Artificial Intelligence Symposium UR-AI 2021 [article]

Karl-Herbert Schäfer
2021 arXiv   pre-print
The alliance's common goal is to reinforce the transfer of knowledge, research, and technology, as well as the cross-border mobility of students.  ...  The TriRhenaTech alliance is a network of universities in the Upper-Rhine Trinational Metropolitan Region comprising of the German universities of applied sciences in Furtwangen, Kaiserslautern, Karlsruhe  ...  Iraki for helpful comments and discussion.  ... 
arXiv:2112.05657v1 fatcat:wdjgymicyrfybg5zth2dc2i3ni

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
2022 arXiv   pre-print
Secondly, we document and summarize hundreds of available alternatives, annotating their domain and supported fairness tasks, along with additional properties of interest for fairness researchers.  ...  We discuss different approaches and levels of attention to these topics, making them tangible, and distill them into a set of best practices for the curation of novel resources.  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc Behaghel, Asia Biega, Marko Bohanec, Chris  ... 
arXiv:2202.01711v2 fatcat:5hf4a42pubc5vnt7tw3al4m5bq

Wasserstein Selective Transfer Learning for Cross-domain Text Mining

Lingyun Feng, Minghui Qiu, Yaliang Li, Haitao Zheng, Ying Shen
2021 Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing   unpublished
The TL module is then trained to minimize the estimated Wasserstein distance in an adversarial manner and provides domain invariant features for the reinforced selector.  ...  Compared with the competing TL approaches, the proposed method selects data samples that are closer to the target domain.  ...  Chen et al. (2018b) propose to minimize the Wasserstein distance between different domains for cross-lingual sentiment classification.  ... 
doi:10.18653/v1/2021.emnlp-main.770 fatcat:jhvts4g5tbe63cqk4cye2336ea

Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation [article]

Masahiro Kato, Takeshi Teshima
2021 arXiv   pre-print
However, BD minimization when applied with highly flexible models, such as deep neural networks, tends to suffer from what we call train-loss hacking, which is a source of overfitting caused by a typical  ...  In this paper, to mitigate train-loss hacking, we propose a non-negative correction for empirical BD estimators.  ...  Acknowledgments The authors would like to thank Hirono Okamoto for his constructive advice. TT was supported by Masason Foundation.  ... 
arXiv:2006.06979v3 fatcat:ypmhbmpql5fq5bu2rkwmpd7lau

A survey on semi-supervised learning

Jesper E. van Engelen, Holger H. Hoos
2019 Machine Learning  
In recent years, research in this area has followed the general trends observed in machine learning, with much attention directed at neural network-based models and generative learning.  ...  Furthermore, we propose a new taxonomy of semi-supervised classification algorithms, which sheds light on the different conceptual and methodological approaches for incorporating unlabelled data into the  ...  Acknowledgements We thank Matthijs van Leeuwen for his valuable feedback on drafts of this article.  ... 
doi:10.1007/s10994-019-05855-6 fatcat:lm2obxiqtrcujfbyzz3erna5p4

Adoption of social software for collaboration

Lei Zhang
2010 Proceedings of the International Conference on Management of Emergent Digital EcoSystems - MEDES '10  
e-commerce, e-learning and e-participation.  ...  E-commerce perspective E-commerce practitioners locate Web technology in the business context. One result of using the electronic network is the rise of co-creation.  ... 
doi:10.1145/1936254.1936301 dblp:conf/medes/Zhang10 fatcat:utdpfvltvvb5lbgvxwqgha27um
« Previous Showing results 1 — 15 out of 53 results