Papers › Wide & Deep Learning for Recommender Systems

Wide & Deep Learning for Recommender Systems

24 Jun 2016arXiv:1606.07792archive 2025-07-28

Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson, Greg Corrado, Wei Chai, Mustafa Ispir, Rohan Anil, Zakaria Haque, Lichan Hong, Vihan Jain, Xiaobing Liu, Hemal Shah

Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more feature engineering effort. With less feature engineering, deep neural networks can generalize better to unseen feature combinations through low-dimensional dense embeddings learned for the sparse features. However, deep neural networks with embeddings can over-generalize and recommend less relevant items when the user-item interactions are sparse and high-rank. In this paper, we present Wide & Deep learning---jointly trained wide linear models and deep neural networks---to combine the benefits of memorization and generalization for recommender systems. We productionized and evaluated the system on Google Play, a commercial mobile app store with over one billion active users and over one million apps. Online experiment results show that Wide & Deep significantly increased app acquisitions compared with wide-only and deep-only models. We have also open-sourced our implementation in TensorFlow.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1606.07792")

Code

Syntology Ran 0 of 5 code samples harvested from 1 repository linked to this paper; 5 have no recorded run.

By repository: community (archive-listed): 5 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

GitHub-HongweiZhang/prediction-flow mentioned on GitHubpytorchMIT report
LeeHyeJin91/Wide_and_Deep mentioned on GitHubtf report
UlionTse/mlgb mentioned on GitHubpytorch report
abmitra84/recommender_system mentioned on GitHub report
aivolcano/RecSys_tf2 mentioned on GitHubtf report
aj9011/Wide-and-Deep mentioned on GitHub report
alsoj/Recommenders-movielens mentioned on GitHubtf report
bytedance/largebatchctr mentioned on GitHubtfApache-2.0 report
codlife/NLP mentioned on GitHub report
fengtong-xiao/DMBGN mentioned on GitHubpytorchBSD-2-Clause report
jsleroux/Recommender-Systems mentioned on GitHubpytorch report
keyuchen886/GoodReads mentioned on GitHub report
massquantity/LibRecommender mentioned on GitHubtfMIT report
qmonmous/BigData-X-Python mentioned on GitHub report
shenweichen/DeepCTR mentioned on GitHubtf report
shenweichen/DeepCTR-Torch mentioned on GitHubpytorchApache-2.0 report
tangxyw/RecAlgorithm mentioned on GitHubtfBSD-2-Clause report
xue-pai/FuxiCTR mentioned on GitHubpytorch report
yil479/yelp_review mentioned on GitHub 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

5 samples harvested; 0 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5unverified

Licence: 5 of the 5 samples are 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 fengtong-xiao/DMBGN. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

gen_dmbgn_input_data fengtong-xiao/DMBGN/models/util.py community (archive-listed) unverified BSD-2-Clause recorded; this copy not marked cleared · pointer only · 3d60fcf4c4f22436 · report
get_ego_network fengtong-xiao/DMBGN/models/VoucherGraphDataset.py community (archive-listed) unverified BSD-2-Clause recorded; this copy not marked cleared · pointer only · 0e35b9b2641f13a8 · report
get_various_action_graphs fengtong-xiao/DMBGN/models/VoucherGraphDataset.py community (archive-listed) unverified BSD-2-Clause recorded; this copy not marked cleared · pointer only · 6559586de402ec2c · report
hash_func fengtong-xiao/DMBGN/models/util.py community (archive-listed) unverified BSD-2-Clause recorded; this copy not marked cleared · pointer only · 93cf3a40870387f9 · report
init_emb fengtong-xiao/DMBGN/models/util.py community (archive-listed) unverified BSD-2-Clause recorded; this copy not marked cleared · pointer only · 347571103fa50431 · report

Tasks

Click-Through Rate PredictionDeep LearningFeature EngineeringMemorizationNews RecommendationRecommendation Systems

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Click-Through Rate Prediction Amazon Wide & Deep AUC 0.8637 #5 of 5 Archive leaderboard report
Click-Through Rate Prediction Bing News Wide & Deep AUC 0.8377 #2 of 7 Archive leaderboard report
Click-Through Rate Prediction Bing News Wide & Deep Log Loss 0.2668 #2 of 7 Archive leaderboard report
Click-Through Rate Prediction Company* Wide & Deep (LR & DNN) AUC 0.8673 #3 of 8 Archive leaderboard report
Click-Through Rate Prediction Company* Wide & Deep (LR & DNN) Log Loss 0.02634 #3 of 8 Archive leaderboard report
Click-Through Rate Prediction Company* Wide & Deep (FM & DNN) AUC 0.8661 #6 of 8 Archive leaderboard report
Click-Through Rate Prediction Company* Wide & Deep (FM & DNN) Log Loss 0.02640 #6 of 8 Archive leaderboard report
Click-Through Rate Prediction Criteo Wide&Deep AUC 0.7981 #37 of 39 Archive leaderboard report
Click-Through Rate Prediction Criteo Wide&Deep Log Loss 0.46772 #37 of 39 Archive leaderboard report
Click-Through Rate Prediction Dianping Wide & Deep AUC 0.8361 #4 of 5 Archive leaderboard report
Click-Through Rate Prediction Dianping Wide & Deep Log Loss 0.3364 #4 of 5 Archive leaderboard report
Click-Through Rate Prediction MovieLens 20M Wide & Deep AUC 0.7304 #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

Introduced by this paper: Wide&Deep

Wide&Deep

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