Filters








62,479 Hits in 3.5 sec

Computing Linear Restrictions of Neural Networks (Presentation)

Matthew Sotoudeh, Aditya V. Thakur
2019 Zenodo  
in each partition close to that of the natural point?  ...  • "Is it possible that there is someone for whom the model recommends 'no approval?'" • Sampling • "What does the model recommend for these N people?" Exploring a New Dimension of Analysis  ... 
doi:10.5281/zenodo.3520103 fatcat:wdvyupkg75aelmeswfe2jcx33i

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  ...  However, success has been accompanied with a major new arising challenge: many applications of machine learning (ML) are adversarial in nature.  ...  advertisements for Point-of-Interest.  ... 
arXiv:2005.10322v2 fatcat:4wqcluqgnbbwpkicunn42et5te

Reflections on Minimal Adversariality

Trudy Govier
2021 Informal Logic  
Although my distinction between minimal and ancillary adversariality is widely accepted, there are flaws in my defense of the claim that all arguments exhibit minimal adversariality and in a lack of sensitivity  ...  Further discussions of minimal adversariality, including those of Scott Aikin, John Casey, Katharina Stevens and Daniel Cohen, are discussed.  ...  Gilbert's model is interesting regarding conflict resolution, extending more broadly than considerations of informal logic would generally recommend.  ... 
doi:10.22329/il.v41i4.6876 fatcat:quqk3lcvfjd7zdusoq24pjfpzu

Gradient Masking Is a Type of Overfitting

Yusuke Yanagita, Masayuki Yamamura
2018 International Journal of Machine Learning and Computing  
Therefore, it is necessary to develop training methods to withstand black-box attacks and conduct studies to investigate the weak points of current NN training.  ...  This paper argues that no special defensive measures are necessary for NN to fall into gradient masking, and it is sufficient to slightly change the initial learning rate of Adam from the recommended value  ...  [3] first pointed out that this sophisticated algorithm may be vulnerable to adversarial examples.  ... 
doi:10.18178/ijmlc.2018.8.3.688 fatcat:lkrvvddmvbhafd35y3uf4dbowe

Adversarial Training Towards Robust Multimedia Recommender System [article]

Jinhui Tang, Xiaoyu Du, Xiangnan He, Fajie Yuan, Qi Tian, Tat-Seng Chua
2019 arXiv   pre-print
To this end, we propose a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning.  ...  Extensive results verify the positive effect of adversarial learning and demonstrate the effectiveness of our AMR method. Source codes are available in https://github.com/duxy-me/AMR.  ...  Regardless of which exact reason, it points to the weak generalization ability of the overall multimedia recommender system -if we imagine the prediction function as a curve in high-dimensional space,  ... 
arXiv:1809.07062v4 fatcat:4jworkx3xzgwnkw2phi3sgr6g4

Query Answering for Existential Rules via Efficient Datalog Rewriting

Zhe Wang, Peng Xiao, Kewen Wang, Zhiqiang Zhuang, Hai Wan
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Moreover, Drewer shows superior or comparable performance over state-of-the-art systems on both the compactness of rewriting and the efficiency of query answering.  ...  We implemented a prototype system Drewer, and experiments show that it is able to handle a wide range of benchmarks in the literature.  ...  Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2020/264 dblp:conf/ijcai/ZhaoSZXB20 fatcat:binzkvxxmjeedhoeepxp6q57vu

Multi-Step Adversarial Perturbations on Recommender Systems Embeddings [article]

Vito Walter Anelli, Alejandro Bellogín, Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra
2020 arXiv   pre-print
Recent advances in adversarial machine learning (AML) in the computer vision domain have raised interests in the security of state-of-the-art model-based recommenders.  ...  task to study the possible weaknesses of embedding-based recommender models under minimal adversarial perturbations.  ...  , point-wise, pair-wise, or even list-wise [2, 23, 31] .  ... 
arXiv:2010.01329v1 fatcat:r6cj424dpnbgjlewv6nza7bh74

DGCN: Diversified Recommendation with Graph Convolutional Networks [article]

Yu Zheng, Chen Gao, Liang Chen, Depeng Jin, Yong Li
2021 arXiv   pre-print
These years much effort has been devoted to improving the accuracy or relevance of the recommendation system.  ...  We propose to perform rebalanced neighbor discovering, category-boosted negative sampling and adversarial learning on top of GCN. We conduct extensive experiments on real-world datasets.  ...  ACKNOWLEDGMENTS This work was supported in part by the National Natural Science Foundation of China under 61941117, U1936217, 61971267, 61972223, 61861136003.  ... 
arXiv:2108.06952v1 fatcat:sdbwxnsndvedvos5tiksaqaria

Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective [article]

Min Gao, Junwei Zhang, Junliang Yu, Jundong Li, Junhao Wen, Qingyu Xiong
2020 arXiv   pre-print
Recommender systems (RSs) now play a very important role in the online lives of people as they serve as personalized filters for users to find relevant items from an array of options.  ...  In recent years, generative adversarial networks (GANs) have garnered increased interest in many fields, owing to their strong capacity to learn complex real data distributions; their abilities to enhance  ...  [84] proposed adversarial point-of-interest recommendation (APOIR), to learn the potential preferences of users in point-of-interest (POI) recommendations.  ... 
arXiv:2003.02474v3 fatcat:wemc7k5mujhrdnmxya5pvt2awi

Private context-aware recommendation of points of interest: An initial investigation

Daniele Riboni, Claudio Bettini
2012 2012 IEEE International Conference on Pervasive Computing and Communications Workshops  
Several context-aware mobile recommender systems have been recently proposed to suggest points of interest (POIs).  ...  Unfortunately, existing POI recommender systems do not provide any formal guarantee of privacy. In this paper, we report an initial investigation of this challenging research issue.  ...  Generally, those systems include a database of points of interest (POIs) belonging to different categories, such as restaurants, pubs, museums, cultural associations, and so on.  ... 
doi:10.1109/percomw.2012.6197582 dblp:conf/percom/RiboniB12 fatcat:oxv3svmtijej3dudcxh7qq4qvy

Membership Inference Attacks Against Recommender Systems [article]

Minxing Zhang, Zhaochun Ren, Zihan Wang, Pengjie Ren, Zhumin Chen, Pengfei Hu, Yang Zhang
2021 arXiv   pre-print
Second, the adversary can only observe the ordered recommended items from a recommender system instead of prediction results in the form of posterior probabilities.  ...  In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference.  ...  In Figure 13 , the red points represent feature vectors of members and the blue points denote feature vectors of nonmembers.  ... 
arXiv:2109.08045v1 fatcat:xtciifcu3neldgubtxgeaxawf4

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  
state-of-the-art performance for item recommendation.  ...  To enhance the robustness of a recommender model and thus improve its generalization performance, we propose a new optimization framework, namely Adversarial Personalized Ranking (APR).  ...  .: AISG-100E-2018-002), and by the National Natural Science Foundation of China under Grant No.: 61702300.  ... 
doi:10.1145/3209978.3209981 dblp:conf/sigir/0001HDC18 fatcat:5ccueqim7fgylh2td52ozszip4

Adversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systems [article]

Siyu Wang, Yuanjiang Cao, Xiaocong Chen, Lina Yao, Xianzhi Wang, Quan Z. Sheng
2021 arXiv   pre-print
Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation  ...  We propose to explore adversarial examples and attack agnostic detection on reinforcement learning-based interactive recommendation systems.  ...  Adversarial attack results. We are interested in how vulnerable the agent is to perturbation in semantic embedding space.  ... 
arXiv:2112.00973v1 fatcat:nqjcqphuujfrhhyfu6gj754sii

PLASTIC: Prioritize Long and Short-term Information in Top-n Recommendation using Adversarial Training

Wei Zhao, Benyou Wang, Jianbo Ye, Yongqiang Gao, Min Yang, Xiaojun Chen
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
In the adversarial process, we train a generator as an agent of reinforcement learning which recommends the next item to a user sequentially.  ...  In this paper, we propose a PLASTIC model, Prioritizing Long And Short-Term Information in top-n reCommendation using adversarial training.  ...  The two point-wise networks of Siamese Network share the same set of parameters. The generator G and the discriminator D are optimized with a minimax two-player game.  ... 
doi:10.24963/ijcai.2018/511 dblp:conf/ijcai/ZhaoWYGYC18 fatcat:e6q7tmhsejb4lgfcn5scsivony

Deep Learning For Virtual Makeup: Transfer, Recommendation And Removal

Amjad Hussien Dr. Taleb Alashkar
2018 Zenodo  
Results The accuracy of the makeup-related facial features classification outperforms current state of the art methods and it succeeds in giving meaningful makeup style recommendations for corrective makeup  ...  Aim To build an advanced e-beauty system for virtual facial makeup that includes: makeup transfer, makeup removal, facial analyzer and makeup recommendation Material and methods The starting point in  ... 
doi:10.5281/zenodo.1184957 fatcat:2nvwg3nhqrambnbie3g7qbb2m4
« Previous Showing results 1 — 15 out of 62,479 results