Papers › Autoencoding Variational Inference For Topic Models

Autoencoding Variational Inference For Topic Models

4 Mar 2017arXiv:1703.01488archive 2025-07-28

Akash Srivastava, Charles Sutton

Topic models are one of the most popular methods for learning representations of text, but a major challenge is that any change to the topic model requires mathematically deriving a new inference algorithm. A promising approach to address this problem is autoencoding variational Bayes (AEVB), but it has proven diffi- cult to apply to topic models in practice. We present what is to our knowledge the first effective AEVB based inference method for latent Dirichlet allocation (LDA), which we call Autoencoded Variational Inference For Topic Model (AVITM). This model tackles the problems caused for AEVB by the Dirichlet prior and by component collapsing. We find that AVITM matches traditional methods in accuracy with much better inference time. Indeed, because of the inference network, we find that it is unnecessary to pay the computational cost of running variational optimization on test data. Because AVITM is black box, it is readily applied to new topic models. As a dramatic illustration of this, we present a new topic model called ProdLDA, that replaces the mixture model in LDA with a product of experts. By changing only one line of code from LDA, we find that ProdLDA yields much more interpretable topics, even if LDA is trained via collapsed Gibbs sampling.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 8 code samples harvested from 3 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 3 repositories, 5 ran (4 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

akashgit/autoencoding_vi_for_topic_models mentioned on GitHubtfMITSyntology: 2 samples, 0 ran · 2 unverified report
is0383kk/Dirichlet_VAE mentioned on GitHubpytorchSyntology: not harvested report
mind-Lab/octis mentioned on GitHubtfMITSyntology: not harvested report
shining-spring/nvlda mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
vlukiyanov/pt-avitm mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
yjxiao/ProdLDA mentioned on GitHubpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
4ran
3unverified

Licence: 1 of the 8 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

akashgit/autoencoding_vi_for_topic_models community (archive-listed) 2 samples, 0 ran · 2 unverified
log_dir_init models/nvlda.py unverified MIT (permissive) · db73bb820e56e989 · report
xavier_init in 18 papers models/nvlda.py unverified MIT (permissive) · ce2f744c3f060169 · report
shining-spring/nvlda community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
read_data in 132 papers examples/prepare_20news_data.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · c7a758418e234da7 · report fixture: signature infile:str/0/str · returned list · level recorded 2026-09-22
vlukiyanov/pt-avitm community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
decoder in 19 papers ptavitm/vae.py ran MIT (permissive) · 8b988d62007ee9ce · report fixture: signature in_dimension:int/0/int, topics:int/0/int, decoder_noise:float/0/float, eps:float/0/float, momentum:float/0/float · returned Sequential · level recorded 2026-09-26
encoder in 30 papers ptavitm/vae.py ran MIT (permissive) · 200ab38e5c9b742f · report fixture: signature in_dimension:int/0/int, hidden1_dimension:int/0/int, hidden2_dimension:int/0/int, encoder_noise:float/0/float · returned Sequential · level recorded 2026-09-26
predict in 126 papers ptavitm/model.py ran MIT (permissive) · c07b9b907915c094 · report fixture: signature dataset:MinimalDataset/0/?, model:callable/0/?, batch_size:int/0/int, cuda:bool/0/bool, silent:bool/0/bool, encode:bool/0/bool, num_workers:int/0/int · returned Tensor · level recorded 2026-09-26
prior in 7 papers ptavitm/vae.py ran fingerprinted MIT (permissive) · 90a17b6a9a9e2d19 · report fixture: signature topics:int/0/int · returned tuple · level recorded 2026-09-26
perplexity in 22 papers ptavitm/model.py unverified MIT (permissive) · 4b4bc8c55147a8c5 · report

Tasks

Topic ModelsVariational Inference

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Topic Models 20NewsGroups ProdLDA C_v 0.35 #6 of 6 Archive leaderboard report
Topic Models AG News ProdLDA C_v 0.32 #6 of 6 Archive leaderboard report
Topic Models AG News ProdLDA NPMI -0.22 #6 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LDA

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections