Papers › Infinite Recommendation Networks: A Data-Centric Approach

Infinite Recommendation Networks: A Data-Centric Approach

3 Jun 2022arXiv:2206.02626archive 2025-07-28

Noveen Sachdeva, Mehak Preet Dhaliwal, Carole-Jean Wu, Julian McAuley

We leverage the Neural Tangent Kernel and its equivalence to training infinitely-wide neural networks to devise ∞-AE: an autoencoder with infinitely-wide bottleneck layers. The outcome is a highly expressive yet simplistic recommendation model with a single hyper-parameter and a closed-form solution. Leveraging ∞-AE's simplicity, we also develop Distill-CF for synthesizing tiny, high-fidelity data summaries which distill the most important knowledge from the extremely large and sparse user-item interaction matrix for efficient and accurate subsequent data-usage like model training, inference, architecture search, etc. This takes a data-centric approach to recommendation, where we aim to improve the quality of logged user-feedback data for subsequent modeling, independent of the learning algorithm. We particularly utilize the concept of differentiable Gumbel-sampling to handle the inherent data heterogeneity, sparsity, and semi-structuredness, while being scalable to datasets with hundreds of millions of user-item interactions. Both of our proposed approaches significantly outperform their respective state-of-the-art and when used together, we observe 96-105% of ∞-AE's performance on the full dataset with as little as 0.1% of the original dataset size, leading us to explore the counter-intuitive question: Is more data what you need for better recommendation?

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="2206.02626")

Code

Syntology Ran 6 of 13 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 7 samples from 2 repositories, 3 ran; community (archive-listed): 6 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

noveens/distill_cf officialmentioned in papermentioned on GitHubjax report
noveens/infinite_ae_cf officialmentioned in papermentioned on GitHubjaxMIT report
AmazingDD/daisyRec mentioned on GitHubpytorch report
recsys-benchmark/daisyrec-v2.0 mentioned on GitHubpytorchMIT 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

13 samples harvested; 6 ran; 0 honoured the contract we drafted; 7 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.

1ran · our draft was wrong
1ran · fixture could not drive it
4ran
7unverified

Licence: 0 of the 13 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

get_item_propensity noveens/infinite_ae_cf/utils.py official repository ran MIT (permissive) · 39c4594180be0c7c · report
get_update_functions noveens/distill_cf/distill.py official repository ran · fixture could not drive it MIT (permissive) · 0030ec204abad735 · report
initialize noveens/distill_cf/distill.py official repository ran · our draft was wrong MIT (permissive) · ba82c8f5022469d4 · report
get_common_path noveens/infinite_ae_cf/utils.py official repository unverified MIT (permissive) · 3ab0f054172cf3f8 · report
get_item_count_map noveens/infinite_ae_cf/utils.py official repository unverified MIT (permissive) · dc1e506d9e302f57 · report
load_raw_dataset noveens/infinite_ae_cf/data.py official repository unverified MIT (permissive) · a16c3bab848068f1 · report
prep_movielens noveens/infinite_ae_cf/preprocess.py official repository unverified MIT (permissive) · ca4b9f603f7b24a2 · report
BPRLoss AmazingDD/daisyRec/daisy/model/EASERecommender.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 44e9a7fc60c3de3c · report
HingeLoss AmazingDD/daisyRec/daisy/model/EASERecommender.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 1e23ad42f13d3766 · report
TOP1Loss AmazingDD/daisyRec/daisy/model/EASERecommender.py community (archive-listed) ran fingerprinted MIT (permissive) · 4819c6d8b7646571 · report
AbstractRecommender AmazingDD/daisyRec/daisy/model/EASERecommender.py community (archive-listed) unverified MIT (permissive) · 56616f78c00e1103 · report
EASE AmazingDD/daisyRec/daisy/model/EASERecommender.py community (archive-listed) unverified MIT (permissive) · bfd5c06502832fdf · report
GeneralRecommender AmazingDD/daisyRec/daisy/model/EASERecommender.py community (archive-listed) unverified MIT (permissive) · 695d9cfdcb0be46e · report

Tasks

Information RetrievalRecommendation Systems

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Recommendation Systems Douban ∞-AE AUC 0.9523 #7 of 7 Archive leaderboard report
Recommendation Systems Douban ∞-AE HR@10 0.2356 #7 of 7 Archive leaderboard report
Recommendation Systems Douban ∞-AE HR@100 0.2837 #7 of 7 Archive leaderboard report
Recommendation Systems Douban ∞-AE PSP@10 0.0128 #7 of 7 Archive leaderboard report
Recommendation Systems Douban ∞-AE nDCG@10 0.2494 #7 of 7 Archive leaderboard report
Recommendation Systems Douban ∞-AE nDCG@100 0.2326 #7 of 7 Archive leaderboard report
Recommendation Systems MovieLens 1M ∞-AE HR@10 0.3151 #24 of 31 Archive leaderboard report
Recommendation Systems MovieLens 1M ∞-AE HR@100 0.6005 #24 of 31 Archive leaderboard report
Recommendation Systems MovieLens 1M ∞-AE PSP@10 0.0322 #24 of 31 Archive leaderboard report
Recommendation Systems MovieLens 1M ∞-AE nDCG@10 0.3282 #24 of 31 Archive leaderboard report
Recommendation Systems MovieLens 1M ∞-AE nDCG@100 0.4253 #24 of 31 Archive leaderboard report
Recommendation Systems Netflix ∞-AE AUC 0.9728 #7 of 10 Archive leaderboard report
Recommendation Systems Netflix ∞-AE PSP@10 0.0375 #7 of 10 Archive leaderboard report
Recommendation Systems Netflix ∞-AE Recall@10 0.2969 #7 of 10 Archive leaderboard report
Recommendation Systems Netflix ∞-AE Recall@100 0.5088 #7 of 10 Archive leaderboard report
Recommendation Systems Netflix ∞-AE nDCG@10 0.3059 #7 of 10 Archive leaderboard report
Recommendation Systems Netflix ∞-AE nDCG@100 0.3659 #7 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.

Methods

NTK

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