31,487 Hits in 2.2 sec

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.  ...  [159, 160] use the adversarial training framework for a neural network-based recommendation model, namely collaborative denoising auto-encoder (CDAE) [149] , based on which the authors propose two  ... 
arXiv:2005.10322v2 fatcat:4wqcluqgnbbwpkicunn42et5te

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
In general, two lines of research have been conducted, and their common ideas can be summarized as follows: (1) for the data noise issue, adversarial perturbations and adversarial sampling-based training  ...  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.  ...  [ATR & DVBPR] In the adversarial training for review-based recommendation (ATR) model, Rafailidis et al. [47] used GANs to generate reviews likely to be relevant to the user's preferences.  ... 
arXiv:2003.02474v3 fatcat:wemc7k5mujhrdnmxya5pvt2awi

RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems [article]

Cheng Wang, Mathias Niepert, Hui Li
2019 arXiv   pre-print
More importantly, RecSys-DAN is highly flexible to both unimodal and multimodal scenarios, and thus it is more robust to the cold-start recommendation which is difficult for previous methods.  ...  The mapping functions in the target domain are learned by playing a min-max game with an adversarial loss, aiming to generate domain indistinguishable representations for a discriminator.  ...  G k v can be either RNN-based (when review texts are used to represent an item) or convolutional neural network (CNN)-based for visual representations (when product image is used to represent an item).  ... 
arXiv:1903.10794v2 fatcat:wy7gqklumjefxn4o36wrkcohzq

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

Yao Zhou, Haonan Wang, Jingrui He, Haixun Wang
2021 arXiv   pre-print
With the prevalence of deep learning based embedding approaches, recommender systems have become a proven and indispensable tool in various information filtering applications.  ...  In this paper, we investigate the dilemma between recommendation and explainability, and show that by utilizing the contextual features (e.g., item reviews from users), we can design a series of explainable  ...  Thus, two types of adversarial recommendation models have been proposed: adversarial learning [11, 27] based RS and GAN-based RS.  ... 
arXiv:2110.14844v1 fatcat:e3s7nbxivzhknidbckjek2hx2e

Why I like it

Yichao Lu, Ruihai Dong, Barry Smyth
2018 Proceedings of the 12th ACM Conference on Recommender Systems - RecSys '18  
and adversarial sequence to sequence learning for explanation generation.  ...  ABSTRACT We describe a novel, multi-task recommendation model, which jointly learns to perform rating prediction and recommendation explanation by combining matrix factorization, for rating prediction,  ...  Adversarial Training for Review Generation with REINFORCE. Now we describe the REINFORCE algorithm for the adversarial training of review generation.  ... 
doi:10.1145/3240323.3240365 dblp:conf/recsys/LuDS18 fatcat:4ipls74wfndzznwho5dw7flcce

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
The idea is to train the model to defend an adversary, which adds perturbations to the target image with the purpose of decreasing the model's accuracy.  ...  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.  ...  RELATED WORK In this section, we briefly review related work on multimedia recommendation and adversarial learning.  ... 
arXiv:1809.07062v4 fatcat:4jworkx3xzgwnkw2phi3sgr6g4

Adversarial Training-based Mean Bayesian Personalized Ranking for Recommender System

Jianfang Wang, Pengfei Han
2019 IEEE Access  
Our implementation is available at: HanXia001/ Adversarial -Training-based-Mean-BPR-for-Recommender.  ...  INDEX TERMS Adversarial training, BPR, collaborative filtering, recommender system.  ...  MBPR BASED ON ADVERSARIAL TRAINING FOR RECOMMENDER SYSTEM To reduce the noise interference in MBPR, we combined MBPR with adversarial training and proposed a novel algorithm, termed as AT-MBPR.  ... 
doi:10.1109/access.2019.2963316 fatcat:urmknb3ekjepfmc64dc4rfylc4

An Empirical Study of DNNs Robustification Inefficacy in Protecting Visual Recommenders [article]

Vito Walter Anelli, Tommaso Di Noia, Daniele Malitesta, Felice Antonio Merra
2020 arXiv   pre-print
Visual-based recommender systems (VRSs) enhance recommendation performance by integrating users' feedback with the visual features of product images extracted from a deep neural network (DNN).  ...  However, since adversarial training techniques have proven to successfully robustify DNNs in preserving classification accuracy, to the best of our knowledge, two important questions have not been investigated  ...  Free Adversarial Training [34] truly eases the computational complexity of standard adversarial training without giving up its effectiveness. Security of Visual-based Recommender Systems.  ... 
arXiv:2010.00984v1 fatcat:oro7ezrotnce7iw6ugb37b32d4

Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels

Lukas Galke, Florian Mai, Iacopo Vagliano, Ansgar Scherp
2018 Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization - UMAP '18  
We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: citation recommendation and subject label recommendation.  ...  By conducting 408 experiments, we show that adversarial regularization consistently improves the performance of autoencoders for recommendation.  ...  The citing 4 Figure 2 : 2 Adversarial autoencoder for item-based recommendations.  ... 
doi:10.1145/3209219.3209236 dblp:conf/um/GalkeMVS18 fatcat:yfevueeu2zarjdffri4z2vdyhq

Fairness-aware Personalized Ranking Recommendation via Adversarial Learning [article]

Ziwei Zhu, Jianling Wang, James Caverlee
2021 arXiv   pre-print
Concretely, we formalize the concepts of ranking-based statistical parity and equal opportunity as two measures of fairness in personalized ranking recommendation for item groups.  ...  In this paper, we re-frame the studied problem as 'item recommendation fairness' in personalized ranking recommendation systems, and provide more details about the training process of the proposed model  ...  parameters Θ for BPR, and Ψ for the adversary; A MODEL TRAINING The model training process for DPR-RSP can be summarized in Algorithm 1, where we train the model in a mini-batch manner.  ... 
arXiv:2103.07849v1 fatcat:g3pnyhdyjbd4hjmla3dkm2mipe

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
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 this paper, we propose the Brand-Topic Model (BTM) which aims to detect brand-associated polarity-bearing topics from product reviews.  ...  For example, based on user profiles and item topics, Gao et al. (2017) dynamically modelled users' interested items for recommendation. Zhang et al. (2015) focused on brand topic tracking.  ... 
arXiv:2101.10150v1 fatcat:hyxyreo5cnenvnwczqil57tqgm

Introduction to the Special Section on Artificial Intelligence Security: Adversarial Attack and Defense

Xiaojiang Du, Willy Susilo, Mohsen Guizani, Zhihong Tian
2021 IEEE Transactions on Network Science and Engineering  
Patel et al. in "KiRTi: A Blockchain-based Credit Recommender System for Financial Institutions" propose KiRTi, a deep-learning-based credit-recommender scheme for public blockchain to facilitate smart  ...  Adversarial learning is one typical defense method, which can migrate such security risk of AI by training with generated adversarial examples.  ... 
doi:10.1109/tnse.2021.3073637 fatcat:ib5qh53qq5bu5hrfjejm3fp76i

Enhancing the Robustness of Neural Collaborative Filtering Systems Under Malicious Attacks

Yali Du, Meng Fang, Jinfeng Yi, Chang Xu, Jun Cheng, Dacheng Tao
2019 IEEE transactions on multimedia  
In this paper, we aim to improve the robustness of recommendation systems based on two concepts: stage-wise hints training and randomness.  ...  To protect a target model, we introduce noise layers in the training of a target model to increase its resistance to adversarial perturbations.  ...  Successful recommendation systems are capable of correctly modeling users' favor over items based on their previous interactions, such as ratings, review comments [4] .  ... 
doi:10.1109/tmm.2018.2887018 fatcat:ulpj5njdindjrbrqvhqsb2v4fy

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  
In short, our APR enhances the pairwise ranking method BPR by performing adversarial training.  ...  item recommendation.  ...  for multi-media recommendation [7] , to model aspects in textual reviews [9] , to recommend items for a group of users [5] , and so on.  ... 
doi:10.1145/3209978.3209981 dblp:conf/sigir/0001HDC18 fatcat:5ccueqim7fgylh2td52ozszip4

An Adversarial Deep Hybrid Model for Text-Aware Recommendation with Convolutional Neural Networks

Xiaolin Zheng, Disheng Dong
2019 Applied Sciences  
Furthermore, we propose an adversarial training framework to learn the hybrid recommendation model, where a generator model is built to learn the distribution over the pairwise ranking pairs while training  ...  The standard matrix factorization methods for recommender systems suffer from data sparsity and cold-start problems.  ...  adversarial training paradigm in learning the data distribution.  ... 
doi:10.3390/app10010156 fatcat:yp7k3zyt5fau7kp4ki6kbz3aau
« Previous Showing results 1 — 15 out of 31,487 results