Advancements in Federated Learning: Models, Methods, and Privacy

Chen, Huiming; Wang, Huandong; Jin, Depeng; Li, Yong

doi:10.48550/arxiv.2302.11466

Cited by 3 publications

(3 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth mentioning that our proposed method is able to scale in large scale networks, and our future work will mainly focus on extending it in federated learning scenarios [41] [42].…”

Section: Discussionmentioning

confidence: 99%

Research on Multilingual News Clustering Based on Cross-Language Word Embeddings

Wu¹,

Li²,

Lam³

2023

Preprint

View full text Add to dashboard Cite

In today's world, news events are emerging incessantly. Classifying the same event reported by different countries is of significant importance for public opinion control and intelligence gathering. Due to the diverse types of news, relying solely on translators would be costly and inefficient, while depending solely on translation systems would incur considerable performance overheads in invoking translation interfaces and storing translated texts. To address this issue, we mainly focus on the clustering problem of cross-lingual news. To be specific, we use a combination of sentence vector representations of news headlines in a mixed semantic space and the topic probability distributions of news content to represent a news article. In the training of cross-lingual models, we employ knowledge distillation techniques to fit two semantic spaces into a mixed semantic space. We abandon traditional static clustering methods like K-Means and AGNES in favor of the incremental clustering algorithm Single-Pass, which we further modify to better suit cross-lingual news clustering scenarios. Our main contributions are as follows: (1) We adopt the English standard BERT as the teacher model and XLM-Roberta as the student model, training a cross-lingual model through knowledge distillation that can represent sentence-level bilingual texts in both Chinese and English. (2) We use the LDA topic model to represent news as a combination of cross-lingual vectors for headlines and topic probability distributions for content, introducing concepts such as topic similarity to address the cross-lingual issue in news content representation. (3) We adapt the Single-Pass clustering algorithm for the news context to make it more applicable. Our optimizations of Single-Pass include adjusting the distance algorithm between samples and clusters, adding cluster merging operations, and incorporating a news time parameter.

show abstract

“…It is worth mentioning that our proposed method is able to scale in large scale networks, and our future work will mainly focus on extending it in federated learning scenarios [41] [42].…”

Section: Discussionmentioning

confidence: 99%

Research on Multilingual News Clustering Based on Cross-Language Word Embeddings

Wu¹,

Li²,

Lam³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Granular connections are formed in the form of intervals, the distribution and quantification of information granularity is the key content of granular neural networks [33]. The granularity of information is distributed among the connections of the neural network in various ways, in order to maximize some specific performance indicators [35] [36]. The allocation protocol is high-dimensional and can be optimized by a variety of optimization algorithms, such as particle swarm optimization, single-parent genetic algorithm, etc.…”

Section: Granular Neural Network Frameworkmentioning

confidence: 99%

The News Delivery Channel Recommendation Based on Granular Neural Network

Liu

2023

Preprint

View full text Add to dashboard Cite

With the continuous maturation and expansion of neural network technology, deep neural networks have been widely utilized as the fundamental building blocks of deep learning in a variety of applications, including speech recognition, machine translation, image processing, and the creation of recommendation systems. Therefore, many re-al-world complex problems can be solved by the deep learning techniques. As is known, traditional news recommendation systems mostly employ techniques based on collaborative filtering and deep learning, but the performance of these algorithms is constrained by the sparsity of the data and the scalability of the approaches. In this paper, we propose a recommendation model using granular neural network model to recommend news to appropriate channels by analyzing the properties of news. Specifically, a specified neural network serves as the foundation for the granular neural network that the model is considered to be build. Different information granularities are attributed to various types of news material, and different information granularities are released between networks in various ways. When processing data, granular output is created, which is compared to the interval values pre-set on various plat-forms and used to quantify the analysis's effectiveness. The analysis results could help the media to match the proper news in depth, maximize the public attention of the news and the utilization of media resources.

show abstract

“…U NCONSTRAINED or constrained optimization problems can be used to formulate many real-world engineering challenges, such as machine learning [32], [38], [45], [46] and wireless communications [18], [19]. The focus of this study is on quasi-Newton approaches for unconstrained optimization problems:…”

Section: Introductionmentioning

confidence: 99%

Incremental Cubic Regularized SR1 Quasi-Newton Method and the Applications in Large-Scale Problems

Jinmin,

Tsang

View full text Add to dashboard Cite

This paper delves into an innovative incremental cubic regularized symmetric rank-1 (SR1) method (ICuREGSR1). By incorporating the cubic regularization technique into SR1, we successfully address the issue of indefinite resulting matrix in SR1. Our core strategy is to adopt an incremental optimization scheme, gradually updating the information of the objective function, which typically involves a sum of multiple independent functions, and is very common in large-scale machine learning tasks. Through numerical experiments on multiple machine learning problems, we find that compared with other traditional algorithms, our proposed algorithm exhibits superior performance in terms of gradient magnitude.

show abstract

Advancements in Federated Learning: Models, Methods, and Privacy

Cited by 3 publications

References 113 publications

Research on Multilingual News Clustering Based on Cross-Language Word Embeddings

Research on Multilingual News Clustering Based on Cross-Language Word Embeddings

The News Delivery Channel Recommendation Based on Granular Neural Network

Incremental Cubic Regularized SR1 Quasi-Newton Method and the Applications in Large-Scale Problems

Contact Info

Product

Resources

About