Papers › Variational Autoencoders for Collaborative Filtering

Variational Autoencoders for Collaborative Filtering

16 Feb 2018arXiv:1802.05814archive 2025-07-28

Dawen Liang, Rahul G. Krishnan, Matthew D. Hoffman, Tony Jebara

We extend variational autoencoders (VAEs) to collaborative filtering for implicit feedback. This non-linear probabilistic model enables us to go beyond the limited modeling capacity of linear factor models which still largely dominate collaborative filtering research.We introduce a generative model with multinomial likelihood and use Bayesian inference for parameter estimation. Despite widespread use in language modeling and economics, the multinomial likelihood receives less attention in the recommender systems literature. We introduce a different regularization parameter for the learning objective, which proves to be crucial for achieving competitive performance. Remarkably, there is an efficient way to tune the parameter using annealing. The resulting model and learning algorithm has information-theoretic connections to maximum entropy discrimination and the information bottleneck principle. Empirically, we show that the proposed approach significantly outperforms several state-of-the-art baselines, including two recently-proposed neural network approaches, on several real-world datasets. We also provide extended experiments comparing the multinomial likelihood with other commonly used likelihood functions in the latent factor collaborative filtering literature and show favorable results. Finally, we identify the pros and cons of employing a principled Bayesian inference approach and characterize settings where it provides the most significant improvements.

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

The archive's official repository (dawenl/vae_cf) was not harvested; the 21 samples below come from 5 community repositories.

Syntology 21 code samples harvested from 5 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 5 repositories, 14 ran (12 with no instrument failure; 2 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

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.

18 repositories listed; official and paper-mentioned ones first.

dawenl/vae_cf officialmentioned in papermentioned on GitHubApache-2.0Syntology: not harvested report
LehengTHU/Agent4Rec mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On Generative Agents in Recommendation (arXiv:2310.10108; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
NamCyan/RecSys-VAE4CF mentioned on GitHubSyntology: not harvested report
amoussawi/recoder mentioned on GitHubpytorchMITSyntology: 7 samples, 4 ran (0 instrument-failed) · 3 unverified report
anonymouspap/latte_recsys mentioned on GitHubpytorchSyntology: not harvested report
cydonia999/variational-autoencoders-for-collaborative-filtering-pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
hasteck/EDLAE_NeurIPS2020 mentioned on GitHubtfApache-2.0Syntology: not harvested report
hasteck/MRF_NeurIPS_2019 mentioned on GitHubApache-2.0Syntology: not harvested report
jvbalen/autoencoders_cf mentioned on GitHubpytorchSyntology: not harvested report
mkfilipiuk/VAE-CF mentioned on GitHubtfApache-2.0Syntology: 7 samples, 4 ran (0 instrument-failed) · 3 unverified report
noob-life/VAE-for-Collaborative-Filtering-Pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
onurboyar/RecommenderSystems mentioned on GitHubSyntology: not harvested report
pyy0715/vae-cf-pyorch mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
rushhan/VAE-for-Collaborative-Filtering-Pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
younggyoseo/vae-cf-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
PreferredAI/cornac pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation (arXiv:2002.02126; that paper's own run record: 6 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; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
jaywonchung/BERT4Rec-VAE-Pytorch pytorchGPL-3.0Syntology: not harvested report
microsoft/recommenders tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Auto-Encoding Variational Bayes (arXiv:1312.6114; that paper's own run record: 140 ran (of which 52 constructed an object rather than computing a result; 120 with no instrument failure: 4 honoured, 2 violated, 114 with no contract checked; 20 where Syntology's instrument failed) · 59 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 7 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.

2ran · our draft was wrong
12ran
7unverified

Licence: 1 of the 21 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 5 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. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

amoussawi/recoder community (archive-listed) 7 samples, 4 ran (0 instrument-failed) · 3 unverified
activation in 30 papers recoder/nn.py ran MIT (permissive) · 6770d02bb49a9b81 · report fixture: signature x:Tensor/2/float, act:str/0/str · returned Tensor · level recorded 2026-09-26
dataframe_to_csr_matrix recoder/utils.py ran MIT (permissive) · 004289d147995228 · report fixture: signature dataframe:DataFrame/0/?, user_col:str/0/str, item_col:str/0/str, inter_col:str/0/str, item_id_map:NoneType/0/?, user_id_map:NoneType/0/? · returned tuple · level recorded 2026-09-26
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
recoder/utils.py ran fingerprinted MIT (permissive) · 71bc7ecec58aab2c · report fixture: signature x:ndarray/2/float, axis:int/0/int · returned ndarray · level recorded 2026-09-26
unzip in 8 papers recoder/utils.py ran MIT (permissive) · 0b263d9c0bf98eef · report fixture: signature l:list/1/tuple · returned list · level recorded 2026-09-26
average_precision in 38 papers recoder/metrics.py unverified MIT (permissive) · 4d7b97afc9598a02 · report
dcg in 14 papers recoder/metrics.py unverified MIT (permissive) · ff00d18b0b2b2c4e · report
recall in 38 papers recoder/metrics.py unverified MIT (permissive) · 2af77108d5dda3c6 · report
cydonia999/variational-autoencoders-for-collaborative-filtering-pytorch community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
get_count in 9 papers create_lastfm.py ran · our draft was wrong MIT (permissive) · 39a54c6a662a97bd · report fixture: signature tp:DataFrame/0/?, id:str/0/str · returned DataFrame · level recorded 2026-09-22
load_weights_pkl utils.py ran MIT (permissive) · 1b0443a94970d13e · report fixture: signature fname:str/0/str · returned dict · level recorded 2026-09-26
filter_triplets create_lastfm.py unverified MIT (permissive) · b5ec9af0318ff9eb · report
mkfilipiuk/VAE-CF community (archive-listed) 7 samples, 4 ran (0 instrument-failed) · 3 unverified
get_users vae/load/parsers.py ran Apache-2.0 (permissive) · 826fc932eb62a3c9 · report fixture: signature files:list/1/str · returned list · level recorded 2026-09-26
make_feedback_implicit vae/load/parsers.py ran Apache-2.0 (permissive) · 66776fde1ecb3000 · report fixture: signature feedback:list/1/float, threshold:float/0/float · returned list · level recorded 2026-09-26
ndcg in 16 papers vae/metrics/ndcg.py ran Apache-2.0 (permissive) · 4026df4b925b1a11 · report fixture: signature X_true:csr_matrix/2/int, X_top_k:ndarray/2/int, R:int/0/int · returned ndarray · level recorded 2026-09-26
recall in 38 papers vae/metrics/recall.py ran Apache-2.0 (permissive) · f65fb0842e61d96e · report fixture: signature X_true:csr_matrix/2/int, X_top_k:ndarray/2/int, R:int/0/int · returned ndarray · level recorded 2026-09-26
decoder_model vae/models/Mult_VAE_model.py unverified Apache-2.0 (permissive) · 66bea44117c43219 · report
get_top_k_sorted vae/utils/top_k.py unverified Apache-2.0 (permissive) · ac973f19c12eeefb · report
get_top_k_sorted_worker vae/utils/top_k.py unverified Apache-2.0 (permissive) · 6dcfff18732766dc · report
pyy0715/vae-cf-pyorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
filter_triplets data.py ran Apache-2.0 (permissive) · 5aa9bf5f5f1e9c45 · report fixture: signature tp:DataFrame/0/?, min_uc:int/0/int, min_sc:int/0/int · returned tuple · level recorded 2026-09-26
split_train_test_proportion data.py ran Apache-2.0 (permissive) · 7918fea013c88cf0 · report fixture: signature data:DataFrame/0/?, test_prop:float/0/float · returned tuple · level recorded 2026-09-26
split_users data.py ran Apache-2.0 (permissive) · 8e8667bf040f2423 · report fixture: signature unique_uid:ndarray/1/int, n_heldout_users:int/0/int · returned tuple · level recorded 2026-09-26
younggyoseo/vae-cf-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
loss_function in 62 papers
census: 7 implementations from 6 papers, 7 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
models.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 615c1c088d110d1a · report fixture: signature recon_x:Tensor/2/float, x:Tensor/2/float, mu:Tensor/2/float, logvar:Tensor/2/float, anneal:float/0/float · returned Tensor · level recorded 2026-09-22

Tasks

Bayesian InferenceCollaborative FilteringLanguage ModelingLanguage ModellingRecommendation Systemsparameter estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Recommendation Systems Million Song Dataset Mult-VAE PR Recall@20 0.266 #5 of 7 Archive leaderboard report
Recommendation Systems Million Song Dataset Mult-VAE PR Recall@50 0.364 #5 of 7 Archive leaderboard report
Recommendation Systems Million Song Dataset Mult-VAE PR nDCG@100 0.316 #5 of 7 Archive leaderboard report
Recommendation Systems Million Song Dataset Mult-DAE Recall@20 0.266 #6 of 7 Archive leaderboard report
Recommendation Systems Million Song Dataset Mult-DAE Recall@50 0.363 #6 of 7 Archive leaderboard report
Recommendation Systems Million Song Dataset Mult-DAE nDCG@100 0.313 #6 of 7 Archive leaderboard report
Recommendation Systems MovieLens 20M Mult-VAE PR Recall@20 0.395 #11 of 18 Archive leaderboard report
Recommendation Systems MovieLens 20M Mult-VAE PR Recall@50 0.537 #11 of 18 Archive leaderboard report
Recommendation Systems MovieLens 20M Mult-VAE PR nDCG@100 0.426 #11 of 18 Archive leaderboard report
Recommendation Systems MovieLens 20M Mult-DAE Recall@20 0.387 #13 of 18 Archive leaderboard report
Recommendation Systems MovieLens 20M Mult-DAE Recall@50 0.524 #13 of 18 Archive leaderboard report
Recommendation Systems MovieLens 20M Mult-DAE nDCG@100 0.419 #13 of 18 Archive leaderboard report
Recommendation Systems Netflix Mult-VAE PR Recall@20 0.351 #5 of 10 Archive leaderboard report
Recommendation Systems Netflix Mult-VAE PR Recall@50 0.444 #5 of 10 Archive leaderboard report
Recommendation Systems Netflix Mult-VAE PR nDCG@100 0.386 #5 of 10 Archive leaderboard report
Recommendation Systems Netflix Mult-DAE Recall@20 0.344 #6 of 10 Archive leaderboard report
Recommendation Systems Netflix Mult-DAE Recall@50 0.438 #6 of 10 Archive leaderboard report
Recommendation Systems Netflix Mult-DAE nDCG@100 0.380 #6 of 10 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.

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