{"id":21280629,"url":"https://github.com/borgwardtlab/topo-ae-distances","last_synced_at":"2026-03-10T12:31:24.960Z","repository":{"id":47213191,"uuid":"300649887","full_name":"BorgwardtLab/topo-ae-distances","owner":"BorgwardtLab","description":null,"archived":false,"fork":false,"pushed_at":"2021-09-08T05:59:35.000Z","size":53020,"stargazers_count":8,"open_issues_count":0,"forks_count":1,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-07-11T11:54:38.359Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BorgwardtLab.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}},"created_at":"2020-10-02T15:00:26.000Z","updated_at":"2022-09-02T17:14:09.000Z","dependencies_parsed_at":"2022-09-03T13:23:26.077Z","dependency_job_id":null,"html_url":"https://github.com/BorgwardtLab/topo-ae-distances","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/BorgwardtLab/topo-ae-distances","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2Ftopo-ae-distances","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2Ftopo-ae-distances/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2Ftopo-ae-distances/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2Ftopo-ae-distances/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BorgwardtLab","download_url":"https://codeload.github.com/BorgwardtLab/topo-ae-distances/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2Ftopo-ae-distances/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30333442,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T05:25:20.737Z","status":"ssl_error","status_checked_at":"2026-03-10T05:25:17.430Z","response_time":106,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":[],"created_at":"2024-11-21T10:37:47.438Z","updated_at":"2026-03-10T12:31:24.932Z","avatar_url":"https://github.com/BorgwardtLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Challenging Euclidean Topological Autoencoders\n\nThis is a follow-up project of the ICML 2020 paper \"Topological Autoencoders\" (reference below).\nHere, we investigate whether domain-specific distance functions in the input space (here image datasets) are necessary for TopoAE, or whether a generic euclidean distance is sufficient. \n[This work](https://openreview.net/pdf?id=P3dZuOUnyEY) has been accepted for presentation at the Neurips 2020 TDA and Beyond workshop. \n\n## References\n\nPlease use the following BibTex code to cite our Neurips 2020 workshop [paper](https://openreview.net/pdf?id=P3dZuOUnyEY):  \n\n```  \n@InProceedings{moor2020challenging,\n    title       = {Challenging Euclidean Topological Autoencoders},\n    author      = {Moor, Michael and Horn, Max and Borgwardt, Karsten and Rieck, Bastian},\n    booktitle   = {NeurIPS 2020 Workshop on Topological Data Analysis and Beyond},\n    year        = {2020},\n    url         = {https://openreview.net/forum?id=P3dZuOUnyEY},\n}\n```  \n\nFurthermore, the original ICML 2020 [paper](https://arxiv.org/abs/1906.00722) proposing Topological Autoencoders in the first place, can be cited as follows:\n\n```\n@InProceedings{Moor19Topological,\n  author        = {Moor, Michael and Horn, Max and Rieck, Bastian and Borgwardt, Karsten},\n  title         = {Topological Autoencoders},\n  year          = {2020},\n  eprint        = {1906.00722},\n  archiveprefix = {arXiv},\n  primaryclass  = {cs.LG},\n  booktitle     = {Proceedings of the 37th International Conference on Machine Learning~(ICML)},\n  series        = {Proceedings of Machine Learning Research},\n  publisher     = {PMLR},\n  pubstate      = {forthcoming},\n}\n```  \n\n## Setup\nIn order to reproduce the results indicated in the workshop paper simply setup an\nenvironment using poetry: \n```bash\npoetry install  \n```\n\n## Running the methods:\nMake sure you have internet access once to be able to download the datasets, and also the vgg model (via the lpips package)\n\nIn case a slurm cluster is available, simply run:  \n```bash  \nsource scripts/run_slurm.sh  \n```  \n\nAlternatively, all jobs can be sequentially/manually called using:  \n```bash  \nsource scripts/run_manual.sh  \n```  \n \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborgwardtlab%2Ftopo-ae-distances","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fborgwardtlab%2Ftopo-ae-distances","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborgwardtlab%2Ftopo-ae-distances/lists"}