On the discriminative power of hyper-parameters in cross-validation and how to choose them

Anelli, Vito Walter; Noia, Tommaso Di; Sciascio, Eugenio Di; Pomo, Claudio; Ragone, Azzurra

doi:10.1145/3298689.3347010

Cited by 16 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, to ensure a fair comparison, we have used the same learning rate to train FedeRank. We have set up the remaining parameters as follows: the user-and positive item-regularization parameter is set to 1/20 of the learning rate; conversely, the negative item-regularization parameter is set to 1/200 of the learning rate as suggested in mymedialite 2 implementation as well as in [4]. Moreover, for each setting, we have selected the best model in the first 20 epochs.…”

Section: Methodsmentioning

confidence: 99%

FedeRank: User Controlled Feedback with Federated Recommender Systems

Anelli¹,

Deldjoo²,

Noia³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Recommender systems have shown to be a successful representative of how data availability can ease our everyday digital life. However, data privacy is one of the most prominent concerns in the digital era. After several data breaches and privacy scandals, the users are now worried about sharing their data. In the last decade, Federated Learning has emerged as a new privacy-preserving distributed machine learning paradigm. It works by processing data on the user device without collecting data in a central repository. In this paper, we present FedeRank, a federated recommendation algorithm. The system learns a personal factorization model onto every device. The training of the global model is modeled as a synchronous process between the central server and the federated clients. FedeRank takes care of computing recommendations in a distributed fashion and allows users to control the portion and type of data they want to share. By comparing with state-of-the-art centralized algorithms, extensive experiments show the effectiveness of FedeRank in terms of recommendation accuracy, even with a small portion of shared user data. Further analysis of the recommendation lists' diversity and novelty guarantees the suitability of the algorithm in real production environments.

show abstract

Section: Methodsmentioning

confidence: 99%

FedeRank: User Controlled Feedback with Federated Recommender Systems

Anelli¹,

Deldjoo²,

Noia³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Regression coefficients based on regression analysis of 1 and 2 versus the linear densities, ı ı ı U and ı ı ı I in Eq (18)…”

mentioning

confidence: 99%

Closed-Form Models of Accuracy Loss due to Subsampling in SVD Collaborative Filtering

Poudel

Bikdash

2023

Big Data Min. Anal.

View full text Add to dashboard Cite

We postulate and analyze a nonlinear subsampling accuracy loss (SSAL) model based on the root mean square error (RMSE) and two SSAL models based on the mean square error (MSE), suggested by extensive preliminary simulations. The SSAL models predict accuracy loss in terms of subsampling parameters like the fraction of users dropped (FUD) and the fraction of items dropped (FID). We seek to investigate whether the models depend on the characteristics of the dataset in a constant way across datasets when using the SVD collaborative filtering (CF) algorithm. The dataset characteristics considered include various densities of the rating matrix and the numbers of users and items. Extensive simulations and rigorous regression analysis led to empirical symmetrical SSAL models in terms of FID and FUD whose coefficients depend only on the data characteristics. The SSAL models came out to be multi-linear in terms of odds ratios of dropping a user (or an item) vs. not dropping it. Moreover, one MSE deterioration model turned out to be linear in the FID and FUD odds where their interaction term has a zero coefficient. Most importantly, the models are constant in the sense that they are written in closed-form using the considered data characteristics (densities and numbers of users and items). The models are validated through extensive simulations based on 850 synthetically generated primary (pre-subsampling) matrices derived from the 25M MovieLens dataset. Nearly 460 000 subsampled rating matrices were then simulated and subjected to the singular value decomposition (SVD) CF algorithm. Further validation was conducted using the 1M MovieLens and the Yahoo! Music Rating datasets. The models were constant and significant across all 3 datasets.

show abstract