FedRec: Federated Recommendation With Explicit Feedback

Lin, Guanyu; Liang, Feng; Pan, Weike; Ming, Zhong

doi:10.1109/mis.2020.3017205

Cited by 107 publications

(83 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, due to users' increasing concerns on privacy leakage, some privacy-preserving recommendation methods have been proposed Flanagan et al, 2020;Lin et al, 2020;Wang et al, 2021;Yang et al, 2021;Wu et al, 2021aWu et al, , 2020a. For example, Chai et al (2019) proposed to compute gradients of user and item embeddings in user clients based on locally stored user rating data and upload gradients to the server for federated model updating.…”

Section: Privacy-preserving Recommendationmentioning

confidence: 99%

Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving

Qi¹,

Wu²,

Wu³

et al. 2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

News recommendation is important for personalized online news services. Most existing news recommendation methods rely on centrally stored user behavior data to both train models offline and provide online recommendation services. However, user data is usually highly privacy-sensitive, and centrally storing them may raise privacy concerns and risks. In this paper, we propose a unified news recommendation framework, which can utilize user data locally stored in user clients to train models and serve users in a privacy-preserving way. Following a widely used paradigm in real-world recommender systems, our framework contains two stages. The first one is for candidate news generation (i.e., recall) and the second one is for candidate news ranking (i.e., ranking). At the recall stage, each client locally learns multiple interest representations from clicked news to comprehensively model user interests. These representations are uploaded to the server to recall candidate news from a large news pool, which are further distributed to the user client at the ranking stage for personalized news display. In addition, we propose an interest decomposer-aggregator method with perturbation noise to better protect private user information encoded in user interest representations. Besides, we collaboratively train both recall and ranking models on the data decentralized in a large number of user clients in a privacy-preserving way. Experiments on two real-world news datasets show that our method can outperform baseline methods and effectively protect user privacy.

show abstract

Section: Privacy-preserving Recommendationmentioning

confidence: 99%

Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving

Qi¹,

Wu²,

Wu³

et al. 2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

show abstract

“…Federated learning (FL) (McMahan et al, 2017) is a privacy-aware technique to learn intelligent models from decentralized data storage, where the raw user data never leaves where it is stored. It has been widely used in many applications like intelligent keyboard (Hard et al, 2018), personalized recommendation (Lin et al, 2020a;, topic modeling (Jiang et al, 2019) and medical natural language processing (Ge et al, 2020). In federated learning, there are usually a number of user devices that locally keep the privacy-sensitive user data, and a server that coordinates these user devices for collaborative model learning.…”

Section: Federated Learningmentioning

confidence: 99%

FedKD: Communication Efficient Federated Learning via Knowledge Distillation

Wu,

Lyu

et al. 2021

Preprint

View full text Add to dashboard Cite

Federated learning is widely used to learn intelligent models from decentralized data. In federated learning, clients need to communicate their local model updates in each iteration of model learning. However, model updates are large in size if the model contains numerous parameters, and there usually needs many rounds of communication until model converges. Thus, the communication cost in federated learning can be quite heavy. In this paper, we propose a communication efficient federated learning method based on knowledge distillation. Instead of directly communicating the large models between clients and server, we propose an adaptive mutual distillation framework to reciprocally learn a student and a teacher model on each client, where only the student model is shared by different clients and updated collaboratively to reduce the communication cost. Both the teacher and student on each client are learned on its local data and the knowledge distilled from each other, where their distillation intensities are controlled by their prediction quality. To further reduce the communication cost, we propose a dynamic gradient approximation method based on singular value decomposition to approximate the exchanged gradients with dynamic precision. Extensive experiments on benchmark datasets in different tasks show that our approach can effectively reduce the communication cost and achieve competitive results.

show abstract

“…Lin et al [14] explored a federated MF system in the context of explicit feedback. Their system, FedRec, randomly samples some unrated items with a parameter 𝜌 ∈ {0, 1, 2, 3} and assigns them a virtual score to hide a user's behavior and enhance the privacy of the participants.…”

Section: Related Workmentioning

confidence: 99%

“…Many of the existing works in the field of federated recommendation systems such as [13,14], rely on the fact that the user's data does not leave the local devices. However, MF-based models use an embedding layer to represent the item profile 1 .…”

Section: Introductionmentioning

confidence: 99%

Federated Neural Collaborative Filtering

Perifanis,

Efraimidis

2021

Preprint

View full text Add to dashboard Cite

In this work, we present a federated version of the state-of-the-art Neural Collaborative Filtering (NCF) approach for item recommendations. The system, named FedNCF, allows learning without requiring users to expose or transmit their raw data. Experimental validation shows that FedNCF achieves comparable recommendation quality to the original NCF system. Although federated learning (FL) enables learning without raw data transmission, recent attacks showed that FL alone does not eliminate privacy concerns. To overcome this challenge, we integrate a privacy-preserving enhancement with a secure aggregation scheme that satisfies the security requirements against an honest-but-curious (HBC) entity, without affecting the quality of the original model. Finally, we discuss the peculiarities observed in the application of FL in a collaborative filtering (CF) task as well as we evaluate the privacy-preserving mechanism in terms of computational cost.

show abstract

FedRec: Federated Recommendation With Explicit Feedback

Cited by 107 publications

References 9 publications

Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving

Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving

FedKD: Communication Efficient Federated Learning via Knowledge Distillation

Federated Neural Collaborative Filtering

Contact Info

Product

Resources

About