Personalized Recommendation Algorithm for Mobile Based on Federated Matrix Factorization

Jia, Junjie; Lei, Zhipeng

doi:10.1088/1742-6596/1802/3/032021

Cited by 9 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the existing context's period information makes the adding appropriate extra relevant to the needs of the users. Researchers of [8] proposed an algorithm that combines matrix error and XGBoost algorithm, storing user's item with SVD ++ algorithm to prevent the effect of many incomplete data on algorithm accuracy. eir model then gets a monitored model for predicting user ratings using the XGBoost features.…”

Section: Introductionmentioning

confidence: 99%

A Personalized Recommendation Algorithm for Political and Ideological Courses in Colleges Using Multiple Interests of Users

Luo

2022

Mobile Information Systems

View full text Add to dashboard Cite

Due to the development of social economy and the continuous growth of science and technology, the historical progress of the information age has opened up. With its mass audience, vast range, and powerful guiding technology, streaming media technology has significantly reduced the time and gap among people in various parts of the world, particularly in the field of education. However, political and ideological education classes in colleges are not sufficiently focused, and as a result, personalized recommendations and analysis of users’ various interests are not possible because of low precision, low user coverage, excessive recommendation time, and poor optimal solution capability. To fill these issues, this study provides a personalized recommendation system for political and ideological courses in colleges based on the interests of multiple users. This paper developed a framework for mining knowledge points in political and ideological course, mined knowledge points in a course using association rules, and calculated the weight of knowledge points using hierarchical tree theory. Apart from these, this paper established the user interest model to obtain the learning characteristics of learners. The experimental results show that the proposed algorithm has higher recommendation accuracy, higher user coverage, short recommendation time, and good optimization ability, which proved that it has a high application value. Based on this study, it can be argued that in modern era of education, the proposed recommendation system of political and ideological education has significant comparative importance for promoting political and ideological education in colleges.

show abstract

Section: Introductionmentioning

confidence: 99%

A Personalized Recommendation Algorithm for Political and Ideological Courses in Colleges Using Multiple Interests of Users

Luo

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…To increase the model capabilities for each client, Jia and Lei incorporated a bias term for the input signals. Additionally, weights on the local devices were adjusted, so that any unreasonable user rating is removed [35]. This results in remaining resource efficient on the client side, while still maintaining the possibility of scaling up.…”

Section: Federated Recommender Systemsmentioning

confidence: 99%

A Privacy Preserving System for Movie Recommendations using Federated Learning

Neumann¹,

Lutz²,

Müller³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recommender systems have become ubiquitous in the past years. They solve the tyranny of choice problem faced by many users, and are employed by many online businesses to drive engagement and sales. Besides other criticisms, like creating filter bubbles within social networks, recommender systems are often reproved for collecting considerable amounts of personal data. However, to personalize recommendations, personal information is fundamentally required. A recent distributed learning scheme called federated learning has made it possible to learn from personal user data without its central collection. Accordingly, we present a complete recommender system for movie recommendations, which provides privacy and thus trustworthiness on two levels: First, it is trained using federated learning and thus is, by its very nature, privacy-preserving, while still enabling individual users to benefit from global insights. And second, a novel federated learning scheme, FedQ, is employed, which not only addresses the problem of non-i.i.d. and small local datasets, but also prevents input data reconstruction attacks by aggregating client models early. To reduce the communication overhead, compression is applied, which significantly reduces the exchanged neural network updates to a fraction of their original data. We conjecture that it may also improve data privacy through its lossy quantization stage.

show abstract

“…Since the embedding model essentially maps each user's interaction behavior into the target item's embedding, it benefits the federated server by helping to identify similar user patterns. However, as described earlier, notwithstanding data heterogeneity and user preference diversity, most FRSs [4,15,39,61,89] simply assume that the parameters of all user models can be directly aggregated. To overcome the non-i.i.d.…”

Section: Server-side Adaptive Model Aggregationmentioning

confidence: 99%

ReFRS: Resource-efficient Federated Recommender System for Dynamic and Diversified User Preferences

Imran¹,

Yin²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Owing to its nature of scalability and privacy by design, federated learning (FL) has received increasing interest in decentralized deep learning. FL has also facilitated recent research on upscaling and privatizing personalized recommendation services, using on-device data to learn recommender models locally. These models are then aggregated globally to obtain a more performant model, while maintaining data privacy. Typically, federated recommender systems (FRSs) do not take into account the lack of resources and data availability at the enddevices. In addition, they assume that the interaction data between users and items is i.i.d. and stationary across end-devices (i.e., users), and that all local recommender models can be directly averaged without considering the user's behavioral diversity. However, in real scenarios, recommendations have to be made on end-devices with sparse interaction data and limited resources. Furthermore, users' preferences are heterogeneous and they frequently visit new items. This makes their personal preferences highly skewed, and the straightforwardly aggregated model is thus ill-posed for such non-i.i.d. data. In this paper, we propose Resource Efficient Federated Recommender System (ReFRS) to enable decentralized recommendation with dynamic and diversified user preferences. On the device side, ReFRS consists of a lightweight self-supervised local model built upon the variational autoencoder for learning a user's temporal preference from a sequence of interacted items. On the server side, ReFRS utilizes a scalable semantic sampler to adaptively perform model aggregation within each identified cluster of similar users. The clustering module operates in an asynchronous and dynamic manner to support efficient global model update and cope with shifting user interests. As a result, ReFRS achieves superior performance in terms of both accuracy and scalability, as demonstrated by comparative experiments on real datasets.

show abstract

Personalized Recommendation Algorithm for Mobile Based on Federated Matrix Factorization

Cited by 9 publications

References 2 publications

A Personalized Recommendation Algorithm for Political and Ideological Courses in Colleges Using Multiple Interests of Users

A Personalized Recommendation Algorithm for Political and Ideological Courses in Colleges Using Multiple Interests of Users

A Privacy Preserving System for Movie Recommendations using Federated Learning

ReFRS: Resource-efficient Federated Recommender System for Dynamic and Diversified User Preferences

Contact Info

Product

Resources

About