{"id":13697075,"url":"https://github.com/akashgit/autoencoding_vi_for_topic_models","last_synced_at":"2025-07-31T14:25:05.664Z","repository":{"id":73766156,"uuid":"73849713","full_name":"akashgit/autoencoding_vi_for_topic_models","owner":"akashgit","description":"Tensorflow implementation for prodLDA and NVLDA.","archived":false,"fork":false,"pushed_at":"2021-04-19T20:39:53.000Z","size":5727,"stargazers_count":253,"open_issues_count":8,"forks_count":52,"subscribers_count":12,"default_branch":"master","last_synced_at":"2025-05-03T17:43:52.248Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://openreview.net/forum?id=BybtVK9lg","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/akashgit.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}},"created_at":"2016-11-15T19:51:50.000Z","updated_at":"2025-04-07T20:02:21.000Z","dependencies_parsed_at":"2023-03-23T23:47:01.792Z","dependency_job_id":null,"html_url":"https://github.com/akashgit/autoencoding_vi_for_topic_models","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/akashgit/autoencoding_vi_for_topic_models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akashgit%2Fautoencoding_vi_for_topic_models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akashgit%2Fautoencoding_vi_for_topic_models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akashgit%2Fautoencoding_vi_for_topic_models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akashgit%2Fautoencoding_vi_for_topic_models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/akashgit","download_url":"https://codeload.github.com/akashgit/autoencoding_vi_for_topic_models/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akashgit%2Fautoencoding_vi_for_topic_models/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268056573,"owners_count":24188538,"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":"2025-07-31T02:00:08.723Z","response_time":66,"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":[],"created_at":"2024-08-02T18:00:52.383Z","updated_at":"2025-07-31T14:25:05.627Z","avatar_url":"https://github.com/akashgit.png","language":"Python","funding_links":[],"categories":["Models","Python"],"sub_categories":["Embedding based Topic Models"],"readme":"# Autoencoding Variational Inference for Topic Models\n\n__UPDATE__\n\n\u003e\u003e Pyro added a prodlDA tutorial: https://pyro.ai/examples/prodlda.html\n\n\u003e\u003e AVITM is now available in OCTIS at https://github.com/MIND-Lab/OCTIS\n\nPlease consider using OCTIS and Pyro versions as they are more upto date.\n\n1. As pointed out by [@govg](https://github.com/govg), this code depends on a slightly older version of TF. I will try to update it soon, in the meantime you can look up a quick fix [here](https://github.com/akashgit/autoencoding_vi_for_topic_models/issues/5) for working with newer version of TF or (3) and (2) below if you'd rather prefer Keras or PyTorch.\n\n2. [@nzw0301](https://github.com/nzw0301) has implemented a [Keras](https://github.com/nzw0301/keras-examples/blob/master/prodLDA.ipynb) version of prodLDA.\n\n3. [@hyqneuron](https://github.com/hyqneuron) recently implemented a [PyTorch](https://github.com/hyqneuron/pytorch-avitm) version of AVITM. So check out his repo.\n\n4. Added `topic_prop` method to both the models. Softmax the output of this method to get the topic proportions.\n\n---\n#### Code for the ICLR 2017 paper: Autoencoding Variational Inference for Topic Models\n---\n\n#### \u003e [Arxiv](https://arxiv.org/abs/1703.01488)\n\n#### \u003e [OpenReview](http://openreview.net/forum?id=BybtVK9lg)\n\n---\n###### This is a tensorflow implementation for both of the Autoencoded Topic Models mentioned in the paper.  \n---\nTo run the `prodLDA` model in the `20Newgroup` dataset:\n\n\u003e `CUDA_VISIBLE_DEVICES=0 python run.py -m prodlda -f 100 -s 100 -t 50 -b 200 -r 0.002 -e 200`\n\nSimilarly for `NVLDA`:\n\n\u003e `CUDA_VISIBLE_DEVICES=0 python run.py -m nvlda -f 100 -s 100 -t 50 -b 200 -r 0.005 -e 300`\n\nCheck `run.py` for other options.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakashgit%2Fautoencoding_vi_for_topic_models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fakashgit%2Fautoencoding_vi_for_topic_models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakashgit%2Fautoencoding_vi_for_topic_models/lists"}