pith. sign in

arxiv: 2605.22924 · v1 · pith:KS6GHWVVnew · submitted 2026-05-21 · 💻 cs.LG · cs.IR

Building a privacy-preserving Federated Recommender system for mobile devices

Aasheesh Singh This is my paper

Pith reviewed 2026-05-25 06:14 UTC · model grok-4.3

classification 💻 cs.LG cs.IR
keywords federated learningrecommender systemsprivacy preservationmobile devicescollaborative filteringon-device inferencetwo-stage pipeline
0
0 comments X

The pith

A two-stage pipeline generates shortlists in the cloud from non-sensitive data then re-ranks them on-device with private context signals.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes a federated recommender that keeps sensitive mobile context data entirely on the device while still producing personalized item rankings. Non-sensitive preference data is used in the cloud for an initial collaborative-filtering shortlist, after which the device applies local signals to reorder the candidates. Only model gradients or updates ever leave the device. The approach is shown to run on MovieLens, activity-recognition data, and a pilot set, and is packaged as a Kotlin Multiplatform library for Android and iOS. The separation directly addresses privacy rules that prohibit central collection of location, sensor, or app-usage context.

Core claim

The central claim is that a two-stage federated recommendation pipeline—cloud-based collaborative filtering on non-sensitive app-context data to produce a shortlist, followed by on-device re-ranking that uses sensitive mobile signals—delivers effective personalization while ensuring the sensitive data never leaves the device and only model updates are transmitted.

What carries the argument

The two-stage federated pipeline that isolates non-sensitive preference data for cloud shortlisting from sensitive context data used only for on-device re-ranking.

If this is right

  • Personalized mobile content can be served without pooling sensitive context data on servers.
  • Training continues via model updates alone, satisfying data-minimization requirements.
  • The same separation pattern can be applied to other on-device personalization tasks.
  • A single Kotlin Multiplatform library makes the pipeline available on both Android and iOS.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The design lowers the regulatory surface area for any app that must handle location or sensor streams.
  • On-device re-ranking may also reduce round-trip latency once the shortlist arrives.
  • If the shortlist quality is high enough, the on-device stage could be made extremely lightweight.

Load-bearing premise

Re-ranking a cloud-generated shortlist on the device with local sensitive signals yields recommendation quality comparable to a model that has direct access to the full centralized dataset.

What would settle it

A controlled experiment that measures precision or recall on held-out user interactions and shows that the on-device re-ranking stage produces materially lower accuracy than a centralized model trained on the same sensitive signals would falsify the claim of effective personalization.

Figures

Figures reproduced from arXiv: 2605.22924 by Aasheesh Singh.

Figure 1.1
Figure 1.1. Figure 1.1: High level architecture of the company’s product offering which is designed for App owners or publishers. The company’s offering consists of a mobile SDK library which is integrated into the app code to provide federated recommendations. Further, a fully managed cloud server coordinates the model weight updates from edge devices with a differential privacy engine. Services such as dashboards and monitori… view at source ↗
Figure 1.2
Figure 1.2. Figure 1.2: Lerna AI’s Dashboard system, monitoring model performance and active mobile devices contributing to the Federated learning network. Project objectives The objectives of the internship were to improve upon the Logistic Regression model for delivering federated recommendations and implement corresponding algorithms from scratch in low-level Kotlin programming language for end-to-end deployment. The tasks p… view at source ↗
Figure 2.1
Figure 2.1. Figure 2.1: Human Activity Recognition pipeline[1]. 11 [PITH_FULL_IMAGE:figures/full_fig_p021_2_1.png] view at source ↗
Figure 2.2
Figure 2.2. Figure 2.2: Data distribution for different Activity classes in UCI Dataset The dataset captures time-series tri-axial acceleration data i.e. (tAcc-XYZ) from accelerometer, where "t" denotes time and the suffix "XYZ" denotes the tri-axial signal in X, Y and Z directions respectively. Additionally, tri-axial angular velocity data from a gyroscope sensor i.e., (tGyro-XYZ) was also recorded to understand rotation infor… view at source ↗
Figure 2.3
Figure 2.3. Figure 2.3: Dimensionality Reduction techniques to better understand UCI HAR Dataset To understand the separation of various Activity classes, we leveraged various dimen￾sionality reduction methods including Principal Component Analysis (PCA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and Pairwise Controlled Manifold Approximation (PaCMAP) on the raw 6 dimensional input signals (3 axis acceleration, 3 gyr… view at source ↗
Figure 2.4
Figure 2.4. Figure 2.4: denotes the class distribution for the above mentioned activities in the real￾life HAR dataset [PITH_FULL_IMAGE:figures/full_fig_p029_2_4.png] view at source ↗
Figure 2.5
Figure 2.5. Figure 2.5: Dimensionality reduction techniques to better understand the Real life HAR dataset 21 [PITH_FULL_IMAGE:figures/full_fig_p031_2_5.png] view at source ↗
Figure 2.6
Figure 2.6. Figure 2.6: Confusion matrix plotted on the Test set for the LSTM model. The model is able to easily differentiate between classes obtaining a macro f1-score of 97.66 %. 2.5.2. Part-B: Testing on a Pilot Dataset In this experiment, we wanted to utilize the trained LSTM model for the activity recognition task as well as the hand-crafted feature embeddings to compare their efficacy against directly inputting sensor da… view at source ↗
Figure 3.1
Figure 3.1. Figure 3.1: The proposed two-stage Recommendation pipeline The first stage, known as the centralized stage, takes item metadata along with non-sensitive user data such as user preferences and item interactions, collectively referred to as App-context data, as described in the previous section. We describe the Correlated Cross-Occurrence based collaborative filtering algorithm deployed in our system in detail in the … view at source ↗
Figure 3.2
Figure 3.2. Figure 3.2: System Architecture diagram detailing various components of the Universal Rec￾ommendation System. The input to the system is comprised of a)Events json containing user-item interactions such as like/purchase etc. and b) Context json containing user/item properties. A sample query to the system is defined in c) Query json and the output d) Rec￾ommendations json are served along with their computed Log-lik… view at source ↗
Figure 4.1
Figure 4.1. Figure 4.1: a) Workflow diagram (source:[16]) of FedAvg training pipeline. b) Training pseudo-code of FedAvg algorithm [30] The model weights across clients are aggregated using a weighted sum, where the weight for each client is defined based on the ratio of training examples for that client to the total 48 [PITH_FULL_IMAGE:figures/full_fig_p058_4_1.png] view at source ↗
Figure 4.2
Figure 4.2. Figure 4.2: Model architecture of the AutoInt CTR model from Fig.1 [40] The AutoInt model architecture consists of 3 modules consisting of an embedding layer, multi-head self-attention transformer layers, and a final MLP layer that outputs sigmoid probabilities. The embedding layer accepts all type of input features: categorical, numerical and multi-valued categorical features and transforms them into a fixed dimens… view at source ↗
Figure 4.3
Figure 4.3. Figure 4.3: Non-IID Distribution of MovieLens 1M dataset across 10 clients. 56 [PITH_FULL_IMAGE:figures/full_fig_p066_4_3.png] view at source ↗
Figure 4.4
Figure 4.4. Figure 4.4: Test AUC and LogLoss plots across federated aggregation rounds for Ablation experiments As observed in the experiment results, federating only the Embedding layer and keeping other parts local performs better than the default All federated setting. For other experi￾ments, such as Attention and Output layer, the Test log loss diverges after a few rounds of training. Note that both Test metrics: AUC and Lo… view at source ↗
read the original abstract

Serving personalized content on mobile devices has traditionally required pooling sensitive user data on centralized servers, a practice increasingly at odds with modern privacy expectations and geographical regulations. We present a two-stage federated recommendation system pipeline for mobile devices, built around a principled separation between non-sensitive user preference data and sensitive mobile context data that never leaves the device. The first stage runs a collaborative filtering model on non-sensitive app-context data in the cloud to generate a shortlist of relevant items. The second stage re-ranks these candidates on-device using sensitive mobile signals, with only model updates/gradients ever leaving the device. We validate the approach on MovieLens, UCI Human Activity Recognition, and a proprietary pilot dataset, and deliver a production-ready implementation as a Kotlin Multiplatform library deployable on Android and iOS.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper proposes a two-stage federated recommender system pipeline for mobile devices. A cloud-based collaborative filtering stage generates a shortlist from non-sensitive user preference data; an on-device stage then re-ranks candidates using sensitive mobile context signals, with only model updates or gradients ever leaving the device. The approach is claimed to have been validated on MovieLens, UCI Human Activity Recognition, and a proprietary pilot dataset, and a production-ready Kotlin Multiplatform library is provided.

Significance. If the on-device re-ranking stage can be shown to deliver non-trivial personalization gains while keeping sensitive data local, the pipeline would address a practical tension between personalization and privacy regulations in mobile recommender systems. The release of a deployable cross-platform library would be a concrete engineering contribution.

major comments (1)
  1. [Abstract] Abstract: the manuscript states that validation occurred on MovieLens, UCI HAR, and a proprietary dataset, yet supplies no metrics (e.g., NDCG@K, precision@K), baselines, ablation results comparing the two-stage pipeline against the cloud stage alone, or error analysis. Without these data the central claim that the on-device re-ranking produces effective privacy-preserving personalization remains unsupported.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback. We address the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the manuscript states that validation occurred on MovieLens, UCI HAR, and a proprietary dataset, yet supplies no metrics (e.g., NDCG@K, precision@K), baselines, ablation results comparing the two-stage pipeline against the cloud stage alone, or error analysis. Without these data the central claim that the on-device re-ranking produces effective privacy-preserving personalization remains unsupported.

    Authors: We agree that the abstract would be strengthened by including key quantitative results. The manuscript body reports evaluation results across the three datasets, including NDCG@K and precision@K metrics, direct comparisons against the cloud-only baseline, ablation studies isolating the on-device re-ranking contribution, and supporting analysis. To make these data immediately visible and address the concern, we will revise the abstract to summarize the main empirical findings (e.g., relative gains from the on-device stage) while retaining the high-level description. We will also verify that an explicit error analysis subsection appears in the results section. This targeted revision directly supports the central claim without altering the technical contribution. revision: yes

Circularity Check

0 steps flagged

No derivation chain present; architectural description only

full rationale

The manuscript describes a two-stage federated pipeline separating non-sensitive and sensitive data, with cloud CF generating a shortlist and on-device re-ranking. No equations, fitted parameters, predictions, or uniqueness theorems appear in the provided text. Validation is asserted on MovieLens, UCI HAR, and a proprietary dataset without any reported metrics or derivations that could reduce to inputs by construction. Self-citations are absent from the abstract and pipeline description. The contribution is therefore self-contained as an engineering architecture with no load-bearing mathematical steps to inspect for circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper presents an applied engineering system rather than a theoretical derivation. No free parameters, axioms, or invented entities are identifiable from the abstract.

pith-pipeline@v0.9.0 · 5654 in / 1172 out tokens · 47965 ms · 2026-05-25T06:14:47.214777+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

47 extracted references · 47 canonical work pages · 3 internal anchors

  1. [1]

    Ac- cessed: May 25, 2026

    Human activity recognition.https://www.v7labs.com/blog/human-activity-recognition. Ac- cessed: May 25, 2026

    work page 2026

  2. [2]

    Website, 2024

    Flower.ai. Website, 2024. URL:https://flower.ai/

    work page 2024

  3. [3]

    Software, 2024

    PyTorch. Software, 2024. URL:https://pytorch.org/

    work page 2024

  4. [4]

    ActionML GitHub Organization

    ActionML. ActionML GitHub Organization. GitHub organization, 2024. URL:https://github.com/ actionml

    work page 2024

  5. [5]

    Universal Recommender

    ActionML. Universal Recommender. GitHub repository, 2024. URL:https://github.com/actionml/ universal-recommender

    work page 2024

  6. [6]

    Endomondo Fitness Trajectories Dataset

    Ahmad P. Endomondo Fitness Trajectories Dataset. Kaggle Dataset, 2023. URL:https://www.kaggle. com/datasets/pypiahmad/endomondo-fitness-trajectories

    work page 2023

  7. [7]

    Anguita, Alessandro Ghio, L

    D. Anguita, Alessandro Ghio, L. Oneto, Xavier Parra, and Jorge Luis Reyes-Ortiz. Hu- man Activity Recognition Using Smartphones. UCI Machine Learning Repository, 2012. DOI: https://doi.org/10.24432/C54S4K

    work page doi:10.24432/c54s4k 2012

  8. [8]

    Anguita, Alessandro Ghio, L

    D. Anguita, Alessandro Ghio, L. Oneto, Xavier Parra, and Jorge Luis Reyes-Ortiz. A public domain dataset for human activity recognition using smartphones. InThe European Symposium on Artificial Neural Networks, 2013. URL:https://api.semanticscholar.org/CorpusID:6975432

    work page 2013

  9. [9]

    Apache Mahout

    Apache Software Foundation. Apache Mahout. Website, 2024. URLhttps://mahout.apache.org/

    work page 2024

  10. [10]

    Apache Spark

    Apache Software Foundation. Apache Spark. Website, 2024. URL:https://spark.apache.org/

    work page 2024

  11. [11]

    Collaborative similarity em- bedding for recommender systems

    Chih-Ming Chen, Chuan-Ju Wang, Ming-Feng Tsai, and Yi-Hsuan Yang. Collaborative similarity em- bedding for recommender systems. InThe World Wide Web Conference, pages 2637–2643, 2019

    work page 2019

  12. [12]

    InProceedings of the 1st workshop on deep learning for recommender systems, pages 7–10, 2016

    Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson, GregCorrado, WeiChai, MustafaIspir, etal.Wide&deeplearningforrecommendersystems. InProceedings of the 1st workshop on deep learning for recommender systems, pages 7–10, 2016

    work page 2016

  13. [13]

    Log likelihood ratios for recommendation algorithms

    Data Science, Adobe Target. Log likelihood ratios for recommendation algorithms. Adobe Ex- perience League, 2024. URL:https://experienceleague.adobe.com/docs/target/assets/ log-likelihood-ratios-recommendation-algorithms.pdf

    work page 2024

  14. [14]

    Using visual features based on mpeg-7 and deep learning for movie recommendation.International journal of multimedia information retrieval, 7:207–219, 2018

    Yashar Deldjoo, Mehdi Elahi, Massimo Quadrana, and Paolo Cremonesi. Using visual features based on mpeg-7 and deep learning for movie recommendation.International journal of multimedia information retrieval, 7:207–219, 2018

    work page 2018

  15. [15]

    Neural Network Matrix Factorization

    Gintare Karolina Dziugaite and Daniel M Roy. Neural network matrix factorization.arXiv preprint arXiv:1511.06443, 2015

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  16. [16]

    What is federated averaging (fedavg)?, 2024

    Educative.io. What is federated averaging (fedavg)?, 2024. URL:https://www.educative.io/ answers/what-is-federated-averaging-fedavg. 64

    work page 2024

  17. [17]

    Universal recommender, 2014

    Pat Ferrel. Universal recommender, 2014. URL:https://www.slideshare.net/pferrel/ unified-recommender-39986309

    work page 2014

  18. [18]

    A public domain dataset for real-life human activity recognition using smartphone sensors.Sensors, 20:2200, 04 2020

    Daniel Garcia-Gonzalez, Daniel Rivero, Enrique Fernandez-Blanco, and Miguel Luaces. A public domain dataset for real-life human activity recognition using smartphone sensors.Sensors, 20:2200, 04 2020. doi:10.3390/s20082200

    work page doi:10.3390/s20082200 2020

  19. [19]

    MovieLens Dataset

    GroupLens. MovieLens Dataset. Website, 2024. URL:https://grouplens.org/datasets/ movielens/

    work page 2024

  20. [20]

    DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

    Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. Deepfm: a factorization- machine based neural network for ctr prediction.arXiv preprint arXiv:1703.04247, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  21. [21]

    Neural collaborative filtering.https://github.com/hexiangnan/neural_ collaborative_filtering, 2024

    Xiangnan He. Neural collaborative filtering.https://github.com/hexiangnan/neural_ collaborative_filtering, 2024

    work page 2024

  22. [22]

    Neural collaborative filtering

    Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collaborative filtering. InProceedings of the 26th international conference on world wide web, pages 173–182, 2017

    work page 2017

  23. [23]

    Human activity recognition on smartphones using a bidirectional lstm network

    Fabio Hernández, Luis F Suárez, Javier Villamizar, and Miguel Altuve. Human activity recognition on smartphones using a bidirectional lstm network. In2019 XXII symposium on image, signal processing and artificial vision (STSIVA), pages 1–5. IEEE, 2019

    work page 2019

  24. [24]

    Collaborative filtering for implicit feedback datasets

    Yifan Hu, Yehuda Koren, and Chris Volinsky. Collaborative filtering for implicit feedback datasets. In 2008 Eighth IEEE international conference on data mining, pages 263–272. Ieee, 2008

    work page 2008

  25. [25]

    Federated collaborative filtering for privacy-preserving personalized recommendation system.CoRR, 2019

    Elena Ivannikova, Suleiman A Khan, Were Oyomno, Qiang Fu, KE Tan, A Flanagan, et al. Federated collaborative filtering for privacy-preserving personalized recommendation system.CoRR, 2019

    work page 2019

  26. [26]

    Kotlin Multiplatform

    JetBrains. Kotlin Multiplatform. Software, 2023. URL:https://kotlinlang.org/docs/ multiplatform.html

    work page 2023

  27. [27]

    harage: a novel multimodal smartwatch-based dataset for human activity recognition

    Adria Mallol-Ragolta, Anastasia Semertzidou, Maria Pateraki, and Björn Schuller. harage: a novel multimodal smartwatch-based dataset for human activity recognition. In2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pages 01–07. IEEE, 2021

    work page 2021

  28. [28]

    Dataset of inertial measurements of smart- phones and smartwatches for human activity recognition.Data in Brief, 51:109809, 2023

    Miguel Matey-Sanz, Sven Casteleyn, and Carlos Granell. Dataset of inertial measurements of smart- phones and smartwatches for human activity recognition.Data in Brief, 51:109809, 2023

    work page 2023

  29. [30]

    Communication-efficient learning of deep networks from decentralized data

    Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. Communication-efficient learning of deep networks from decentralized data. InArtificial intelligence and statistics, pages 1273–1282. PMLR, 2017

    work page 2017

  30. [31]

    AnExpositoryNote.Thelikelihoodratio, wald, andlagrangemultipliertests.The American Statistician, 36(3 Part 1):153–157, 1982

    work page 1982

  31. [32]

    Together is better: Hybrid recommendations combining graph embeddings and contextualized word representa- tions

    Marco Polignano, Cataldo Musto, Marco de Gemmis, Pasquale Lops, and Giovanni Semeraro. Together is better: Hybrid recommendations combining graph embeddings and contextualized word representa- tions. InProceedings of the 15th ACM conference on recommender systems, pages 187–198, 2021. 65

    work page 2021

  32. [33]

    Factorization machines

    Steffen Rendle. Factorization machines. In2010 IEEE International conference on data mining, pages 995–1000. IEEE, 2010

    work page 2010

  33. [34]

    BPR: Bayesian Personalized Ranking from Implicit Feedback

    Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback.arXiv preprint arXiv:1205.2618, 2012

    work page internal anchor Pith review Pith/arXiv arXiv 2012

  34. [35]

    Deep convolutional neural networks for human activity recog- nition with smartphone sensors

    Charissa Ann Ronao and Sung-Bae Cho. Deep convolutional neural networks for human activity recog- nition with smartphone sensors. InNeural Information Processing: 22nd International Conference, ICONIP 2015, November 9-12, 2015, Proceedings, Part IV 22, pages 46–53. Springer, 2015

    work page 2015

  35. [36]

    Item-based collaborative filtering recommendation algorithms

    Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. Item-based collaborative filtering recommendation algorithms. InProceedings of the 10th international conference on World Wide Web, pages 285–295, 2001

    work page 2001

  36. [37]

    Scalable similarity-based neighborhood meth- ods with mapreduce

    Sebastian Schelter, Christoph Boden, and Volker Markl. Scalable similarity-based neighborhood meth- ods with mapreduce. InProceedings of the sixth ACM conference on Recommender systems, pages 163–170, 2012

    work page 2012

  37. [38]

    Model evaluation: Balanced accuracy score, 2024

    scikit-learn contributors. Model evaluation: Balanced accuracy score, 2024. URL:https: //scikit-learn.org/stable/modules/model_evaluation.html#balanced-accuracy-score

    work page 2024

  38. [39]

    Hu- man activity recognition using multichannel convolutional neural network

    Niloy Sikder, Md Sanaullah Chowdhury, Abu Shamim Mohammad Arif, and Abdullah-Al Nahid. Hu- man activity recognition using multichannel convolutional neural network. In2019 5th International conference on advances in electrical engineering (ICAEE), pages 560–565. IEEE, 2019

    work page 2019

  39. [40]

    Autoint: Automatic feature interaction learning via self-attentive neural networks

    Weiping Song, Chence Shi, Zhiping Xiao, Zhijian Duan, Yewen Xu, Ming Zhang, and Jian Tang. Autoint: Automatic feature interaction learning via self-attentive neural networks. InProceedings of the 28th ACM international conference on information and knowledge management, pages 1161–1170, 2019

    work page 2019

  40. [41]

    IJCAI-16 Brick-and-Mortar Store Recommendation Dataset, 2018

    Tianchi. IJCAI-16 Brick-and-Mortar Store Recommendation Dataset, 2018. URL:https://tianchi. aliyun.com/dataset/dataDetail?dataId=53

    work page 2018

  41. [42]

    Collaborative filtering em- beddings for memory-based recommender systems.Engineering Applications of Artificial Intelligence, 85:347–356, 2019

    Daniel Valcarce, Alfonso Landin, Javier Parapar, and Álvaro Barreiro. Collaborative filtering em- beddings for memory-based recommender systems.Engineering Applications of Artificial Intelligence, 85:347–356, 2019

    work page 2019

  42. [43]

    Yingfan Wang, Haiyang Huang, Cynthia Rudin, and Yaron Shaposhnik. Understanding how dimension reduction tools work: An empirical approach to deciphering t-sne, umap, trimap, and pacmap for data visualization.Journal of Machine Learning Research, 22(201):1–73, 2021. URL:http://jmlr.org/ papers/v22/20-1061.html

    work page 2021

  43. [44]

    Federated learning with differential privacy: Algorithms and performance analysis

    Kang Wei, Jun Li, Ming Ding, Chuan Ma, Howard H Yang, Farhad Farokhi, Shi Jin, Tony QS Quek, and H Vincent Poor. Federated learning with differential privacy: Algorithms and performance analysis. IEEE transactions on information forensics and security, 15:3454–3469, 2020

    work page 2020

  44. [45]

    Personalized recommendation with knowledge graph via dual- autoencoder.Applied Intelligence, 52(6):6196–6207, 2022

    Yang Yang, Yi Zhu, and Yun Li. Personalized recommendation with knowledge graph via dual- autoencoder.Applied Intelligence, 52(6):6196–6207, 2022

    work page 2022

  45. [46]

    Yelp Dataset

    Yelp. Yelp Dataset. Website, 2024. URL:https://www.yelp.com/dataset/

    work page 2024

  46. [47]

    Deep interest network for click-through rate prediction

    Guorui Zhou, Xiaoqiang Zhu, Chenru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, and Kun Gai. Deep interest network for click-through rate prediction. InProceedings of the 66 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 1059–1068, 2018

    work page 2018

  47. [48]

    Retailrocket recommender system dataset, 2022

    Roman Zykov, Noskov Artem, and Anokhin Alexander. Retailrocket recommender system dataset, 2022. URL:https://www.kaggle.com/dsv/4471234,doi:10.34740/KAGGLE/DSV/4471234. 67

    work page doi:10.34740/kaggle/dsv/4471234 2022