Papers › Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems

Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems

25 Sep 2019arXiv:1909.11810archive 2025-07-28

Antonio Ginart, Maxim Naumov, Dheevatsa Mudigere, Jiyan Yang, James Zou

Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive -- potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized memory consumption, we explore mixed dimension embeddings, an embedding layer architecture in which a particular embedding vector's dimension scales with its query frequency. Through theoretical analysis and systematic experiments, we demonstrate that using mixed dimensions can drastically reduce the memory usage, while maintaining and even improving the ML performance. Empirically, we show that the proposed mixed dimension layers improve accuracy by 0.1% using half as many parameters or maintain it using 16X fewer parameters for click-through rate prediction task on the Criteo Kaggle dataset.

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 26 code samples harvested from 4 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 13 samples from 3 repositories, 11 ran (10 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/dlrm officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 10 ran (0 instrument-failed) · 3 unverified report
JShubhM15/recommender_systems mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
myungkeun-cho/taobao_dlrm mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Learning Recommendation Model for Personalization and Recommendation Systems (arXiv:1906.00091; that paper's own run record: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
nikithamalgifb/dlrm mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Learning Recommendation Model for Personalization and Recommendation Systems (arXiv:1906.00091; that paper's own run record: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
samiwilf/dlrm_from_shz0116 mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
soycoder/dlrm-fb mentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified 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

26 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 5 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 · honoured contract
1ran · our draft was wrong
19ran
5unverified

Licence: 26 of the 26 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 4 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.

facebookresearch/dlrm official repository 13 samples, 10 ran (0 instrument-failed) · 3 unverified
collate_wrapper_criteo dlrm_data_caffe2.py ran MIT recorded; this copy not marked cleared · pointer only · 283f3ba4a908ce84 · report fixture: signature list_of_tuples:list/1/tuple · returned tuple · level recorded 2026-09-25
collate_wrapper_criteo_length dlrm_data_pytorch.py ran MIT recorded; this copy not marked cleared · pointer only · a09d6b455a2c4a47 · report fixture: signature list_of_tuples:list/1/tuple · returned tuple · level recorded 2026-09-25
collate_wrapper_criteo_offset dlrm_data_pytorch.py ran MIT recorded; this copy not marked cleared · pointer only · 8308da72d2675175 · report fixture: signature list_of_tuples:list/1/tuple · returned tuple · level recorded 2026-09-25
convertUStringToDistinctIntsDict data_utils.py ran MIT recorded; this copy not marked cleared · pointer only · 0035cd64b0d2bc24 · report fixture: signature mat:ndarray/2/object, convertDicts:list/1/dict, counts:list/1/int · returned tuple · level recorded 2026-09-25
convertUStringToDistinctIntsUnique data_utils.py ran MIT recorded; this copy not marked cleared · pointer only · 892c2beb0c55d9bd · report fixture: signature mat:ndarray/2/float, mat_uni:list/1/ndarray, counts:list/1/int · returned tuple · level recorded 2026-09-25
env2int extend_distributed.py ran MIT recorded; this copy not marked cleared · pointer only · 79aced565146dde0 · report fixture: signature env_list:list/1/str, default:int/0/int · returned int · level recorded 2026-09-25
get_my_slice extend_distributed.py ran MIT recorded; this copy not marked cleared · pointer only · 4f418abdfe835117 · report fixture: signature n:int/0/int · returned slice · level recorded 2026-09-25
get_split_lengths extend_distributed.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 9b49f14a64e85b94 · report fixture: signature n:int/0/int · returned tuple · level recorded 2026-09-25
parse_args in 355 papers torchrec_dlrm/dlrm_main.py ran MIT recorded; this copy not marked cleared · pointer only · bc76972abcd25ad9 · report fixture: signature argv:list/1/str · returned Namespace · level recorded 2026-09-25
unpack_batch dlrm_data_caffe2.py ran MIT recorded; this copy not marked cleared · pointer only · 599f18ad1d67a083 · report fixture: signature b:tuple/1/Tensor, data_gen:callable/0/?, data_set:object/0/? · returned tuple · level recorded 2026-09-25
concatCriteoAdData data_utils.py unverified MIT recorded; this copy not marked cleared · pointer only · c1637c05b55a3b1f · report
offset_to_length_converter dlrm_data_pytorch.py unverified MIT recorded; this copy not marked cleared · pointer only · 3c72bf5adfd7003e · report
offset_to_length_convertor dlrm_data_caffe2.py unverified MIT recorded; this copy not marked cleared · pointer only · d85ff8802ff97151 · report
JShubhM15/recommender_systems community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
alpha_power_rule tricks/md_embedding_bag.py ran MIT recorded; this copy not marked cleared · pointer only · fd113bb4fcc68aa4 · report fixture: signature n:Tensor/1/int, alpha:float/0/float, d0:float/0/float, B:NoneType/0/? · returned Tensor · level recorded 2026-09-24
collate_wrapper_random dlrm_data_pytorch.py ran MIT recorded; this copy not marked cleared · pointer only · f2e2bab9a2fd0232 · report fixture: signature list_of_tuples:list/1/tuple · returned tuple · level recorded 2026-09-24
generate_random_data dlrm_data_caffe2.py ran MIT recorded; this copy not marked cleared · pointer only · 1097ff7819bbee7c · report fixture: signature m_den:int/0/int, ln_emb:list/1/int, data_size:int/0/int, num_batches:int/0/int, mini_batch_size:int/0/int, num_indices_per_lookup:int/0/int, num_indices_per_lookup_fixed:bool/0/bool, num_targets:int/0/int, round_targets:bool/0/bool, data_generation:str/0/str, trace_file:str/0/str, enable_padding:bool/0/bool · returned tuple · level recorded 2026-09-24
generate_random_output_batch dlrm_data_caffe2.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · cbb88ac844c2df5f · report fixture: signature n:int/0/int, num_targets:int/0/int, round_targets:bool/0/bool · returned ndarray · level recorded 2026-09-24
md_solver tricks/md_embedding_bag.py ran MIT recorded; this copy not marked cleared · pointer only · 4f4be21cdbb66f71 · report fixture: signature n:Tensor/1/int, alpha:Tensor/0/float, d0:Tensor/0/float, B:NoneType/0/?, round_dim:bool/0/bool, k:Tensor/1/int · returned Tensor · level recorded 2026-09-24
pow_2_round tricks/md_embedding_bag.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 80622eb9563659f7 · report fixture: signature dims:Tensor/1/int · returned Tensor · level recorded 2026-09-24
samiwilf/dlrm_from_shz0116 community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
calculate_metrics in 61 papers dlrm_s_caffe2.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 332764c725473589 · report fixture: signature targets:list/1/ndarray, scores:list/1/ndarray · returned dict · level recorded 2026-09-22
generate_random_data dlrm_data.py ran MIT recorded; this copy not marked cleared · pointer only · 9da41185c4785d9a · report fixture: signature m_den:int/0/int, ln_emb:list/1/int, data_size:int/0/int, num_batches:int/0/int, mini_batch_size:int/0/int, num_indices_per_lookup:int/0/int, num_indices_per_lookup_fixed:bool/0/bool, num_targets:int/0/int, round_targets:bool/0/bool, data_generation:str/0/str, trace_file:str/0/str, enable_padding:bool/0/bool · returned tuple · level recorded 2026-09-24
make_random_data_and_loader dlrm_data.py ran MIT recorded; this copy not marked cleared · pointer only · 69f5fa52cad838f2 · report fixture: signature args:ArgsStandIn/0/?, ln_emb:list/1/int, m_den:int/0/int · returned tuple · level recorded 2026-09-24
soycoder/dlrm-fb community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
md_solver tricks/md_embedding_bag.py ran MIT recorded; this copy not marked cleared · pointer only · 2040f298de85ebb4 · report fixture: signature n:Tensor/1/int, alpha:Tensor/0/float, d0:Tensor/0/float, B:NoneType/0/?, round_dim:bool/0/bool, k:Tensor/1/int · returned Tensor · level recorded 2026-09-24
time_wrap dlrm_s_pytorch.py ran · honoured contract MIT recorded; this copy not marked cleared · pointer only · 0b825b705dac66c0 · report fixture: signature use_gpu:bool/0/bool · returned float · level recorded 2026-09-22
dlrm_wrap dlrm_s_pytorch.py unverified MIT recorded; this copy not marked cleared · pointer only · afee36a6506b0fa7 · report
loss_fn_wrap dlrm_s_pytorch.py unverified MIT recorded; this copy not marked cleared · pointer only · 0e5d7c0e5fed2a07 · report

Tasks

Click-Through Rate PredictionCollaborative FilteringRecommendation Systems

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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