{"id":23743152,"url":"https://github.com/juselara1/dmae","last_synced_at":"2025-09-04T18:31:42.038Z","repository":{"id":39723367,"uuid":"272638488","full_name":"juselara1/dmae","owner":"juselara1","description":"TensorFlow implementation of the Dissimilarity Mixture Autoencoder: https://arxiv.org/abs/2006.08177","archived":false,"fork":false,"pushed_at":"2022-12-08T07:59:57.000Z","size":10423,"stargazers_count":10,"open_issues_count":10,"forks_count":4,"subscribers_count":4,"default_branch":"main","last_synced_at":"2023-03-08T22:38:51.185Z","etag":null,"topics":["autoencoder","clustering","deep-clustering","deep-learning","dissimilarity-mixture-autoencoder","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","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/juselara1.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":"2020-06-16T07:24:40.000Z","updated_at":"2021-10-25T15:37:11.000Z","dependencies_parsed_at":"2023-01-25T09:15:52.320Z","dependency_job_id":null,"html_url":"https://github.com/juselara1/dmae","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juselara1%2Fdmae","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juselara1%2Fdmae/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juselara1%2Fdmae/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juselara1%2Fdmae/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/juselara1","download_url":"https://codeload.github.com/juselara1/dmae/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":231982169,"owners_count":18455675,"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","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":["autoencoder","clustering","deep-clustering","deep-learning","dissimilarity-mixture-autoencoder","tensorflow"],"created_at":"2024-12-31T11:58:37.414Z","updated_at":"2024-12-31T11:58:37.939Z","avatar_url":"https://github.com/juselara1.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Dissimilarity Mixture Autoencoder for Deep Clustering\n\n\u003ca href=\"https://pypi.python.org/pypi/dmae\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/dmae.svg\"/\u003e\u003c/a\u003e\n\u003ca href=\"https://hub.docker.com/repository/docker/juselara/dmae\"\u003e\u003cimg src=\"https://img.shields.io/badge/docker-v1.1.2-blue\"\u003e\u003c/a\u003e\n\u003ca href='https://dmae.readthedocs.io/en/latest/?badge=latest'\u003e\n    \u003cimg src='https://readthedocs.org/projects/dmae/badge/?version=latest' alt='Documentation Status' /\u003e\n\u003c/a\u003e\n\nTensorflow implementation of the Dissimilarity Mixture Autoencoder:\n\n* Juan S. Lara and Fabio A. González. [\"Dissimilarity Mixture Autoencoder for Deep Clustering\"](https://arxiv.org/abs/2006.08177) arXiv preprint arXiv:2006.08177 (2020).\n\n## Abstract\n\nThe dissimilarity mixture autoencoder (DMAE) is a neural network model for feature-based clustering that incorporates a flexible dissimilarity function and can be integrated into any kind of deep learning architecture. It internally represents a dissimilarity mixture model (DMM) that extends classical methods like Bregman clustering to any convex and differentiable dissimilarity function through the reinterpretation of probabilistic notions as neural network components. Likewise, it leverages from unsupervised representation learning, allowing a simultaneous learning of the clusters and neural network's parameters. Experimental evaluation was performed on image and text clustering benchmark datasets showing that DMAE is competitive in terms of unsupervised classification accuracy and normalized mutual information.\n\n## Usage and Documentation\n\nYou can check the official `dmae` [documentation](https://dmae.readthedocs.io/en/latest/index.html).\n\n## Gallery and Examples\n\n* Deep architecture:\n\n    ![dmae](https://raw.githubusercontent.com/larajuse/Resources/master/dmae/dmae.svg)\n\n* Clustering examples:\n    ![clustering](https://raw.githubusercontent.com/juselara1/Resources/master/dmae/clustering_examples.svg)\n\n* Probabilistic interpretations:\n    ![probabilistic](https://raw.githubusercontent.com/juselara1/Resources/master/dmae/probabilistic.svg)\n\nThese examples and the paper replication experiments can be found in the [examples](https://github.com/juselara1/dmae/tree/main/examples) folder.\n\n## Installation\n\nYou can install `dmae` from PyPi using `pip`, building from source or pulling a preconfigured docker image.\n\n### PyPi\n\nTo install `dmae` using `pip` you can run the following command:\n\n```sh\npip install dmae\n```\n\n*(optional) If you have an environment with the nvidia drivers and CUDA, you can instead run:*\n\n```sh\npip install dmae-gpu\n```\n\n### Source\n\nYou can clone this repository:\n\n```sh\ngit clone https://github.com/juselara1/dmae.git\n```\n\nInstall the requirements:\n\n```sh\npip install -r requirements.txt\n```\n\n*(optional) If you have an environment with the nvidia drivers and CUDA, you can instead run:*\n\n```sh\npip install -r requiremets-gpu.txt\n```\n\nFinally, you can install `dmae` via setuptools:\n\n```sh\npip install --no-deps .\n```\n\n### Docker \n\nYou can pull a preconfigured docker image with `dmae` from DockerHub:\n\n```sh\ndocker pull juselara/dmae:latest\n```\n\n*(optional) If you have an environment with the nvidia drivers installed, you can instead run:*\n\n```sh\ndocker pull juselara/dmae:latest-gpu\n```\n\n## Citation\n\n```\n@misc{lara2020dissimilarity,\n      title={Dissimilarity Mixture Autoencoder for Deep Clustering}, \n      author={Juan S. Lara and Fabio A. González},\n      year={2020},\n      eprint={2006.08177},\n      archivePrefix={arXiv},\n      primaryClass={cs.LG}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjuselara1%2Fdmae","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjuselara1%2Fdmae","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjuselara1%2Fdmae/lists"}