{"id":25582590,"url":"https://github.com/joserapa98/tensorization-nns","last_synced_at":"2025-07-24T22:05:19.519Z","repository":{"id":278229114,"uuid":"934916039","full_name":"joserapa98/tensorization-nns","owner":"joserapa98","description":"Code repository for arXiv:2501.06300","archived":false,"fork":false,"pushed_at":"2025-06-11T11:29:40.000Z","size":5831,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-11T12:39:17.444Z","etag":null,"topics":["efficiency","initialization","interpretability","machine-learning","privacy","tensor-networks"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2501.06300","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/joserapa98.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-02-18T15:59:17.000Z","updated_at":"2025-06-11T11:29:43.000Z","dependencies_parsed_at":null,"dependency_job_id":"95f31828-76b1-4a7c-b07e-221799d53445","html_url":"https://github.com/joserapa98/tensorization-nns","commit_stats":null,"previous_names":["joserapa98/tensorization-nns"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/joserapa98/tensorization-nns","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joserapa98%2Ftensorization-nns","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joserapa98%2Ftensorization-nns/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joserapa98%2Ftensorization-nns/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joserapa98%2Ftensorization-nns/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/joserapa98","download_url":"https://codeload.github.com/joserapa98/tensorization-nns/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/joserapa98%2Ftensorization-nns/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266909755,"owners_count":24004736,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-24T02:00:09.469Z","response_time":99,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["efficiency","initialization","interpretability","machine-learning","privacy","tensor-networks"],"created_at":"2025-02-21T05:17:36.069Z","updated_at":"2025-07-24T22:05:19.507Z","avatar_url":"https://github.com/joserapa98.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![DOI](https://zenodo.org/badge/934916039.svg)](https://doi.org/10.5281/zenodo.15639936)\n\n# [Tensorization of neural networks for improved privacy and interpretability](https://arxiv.org/abs/2501.06300)\n\n**José Ramón Pareja Monturiol, Alejandro Pozas-Kerstjens, David Pérez-García**\n\n\nThis repository contains all the code used to run the experiments in the paper,\nincluding the tuning and training of neural network models, tensorizing them,\nand training tensor train models.  \n\nThe code for the TT-RSS decomposition is not included in this repository, as it\nis already available in [TensorKrowch](https://github.com/joserapa98/tensorkrowch).  \n\n\n## Requirements\n\n* python \u003e= 3.8\n\n**Tensor network models**\n* tensorkrowch == 1.1.6\n\nInstall via:\n```\npip install tensorkrowch==1.1.6\n```\n\n**Deep learning framework** (versions specified by TensorKrowch)\n* torch\n* torchvision  \n* torchaudio  \n\n**Hyperparameter tuning**\n* ray \u003e= 2.37.0\n\nInstall via:\n```\npip install -U \"ray[data,train,tune,serve]\"\n```\n\n**Packages for figures**\n* matplotlib\n* seaborn\n\nTo use $\\LaTeX$ in figure texts, make sure it is installed on your system.\n\n\n## Instructions\n\nTo run the experiments, follow the instructions in each `guide` file, starting\nwith the one in the parent folder, which explains how to create the necessary\ndatasets.  \n\nThe code for the different experiments is located in the corresponding subfolders\ninside the `experiments` directory. Each subfolder contains a `guide` file with\ninstructions on how to run the code. The parameters are preconfigured to reproduce\nthe results presented in the paper.  \n\nExperiments are intended to be run sequentially, from `0_train_nns` to `6_privacy`.\nHowever, if you are only interested in a specific experiment, you may not need\nto run all of them. In that case, ensure that any required prior experiments\nhave been completed.  \n\nAll scripts should be executed from the parent folder.  \n\n\n## Citing\n\nIf you would like to cite this work, please use the following format:\n\n- J. R. Pareja Monturiol, A. Pozas-Kerstjens, D. Pérez-García, \"Tensorization\nof neural networks for improved privacy and interpretability\" (2025), arXiv:2501.06300\n\n```\n@misc{pareja2025tensorization,\n  title={Tensorization of neural networks for improved privacy and interpretability}, \n  author={Pareja Monturiol, José Ramón and Pozas-Kerstjens, Alejandro and Pérez-García, David},\n  year={2025},\n  eprint={2501.06300},\n  archivePrefix={arXiv},\n  primaryClass={math.NA},\n  url={https://arxiv.org/abs/2501.06300}, \n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjoserapa98%2Ftensorization-nns","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjoserapa98%2Ftensorization-nns","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjoserapa98%2Ftensorization-nns/lists"}