SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.02604 · ICLR · 2025

Long-Sequence Recommendation Models Need Decoupled Embeddings

Qian Li, Mingsheng Long, Baixu Chen, Junwei Pan, Ximei Wang, Jie Jiang, Jialong Wu, Ningya Feng, Xian Hu

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 4 violated it and 2 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.02604.json · badge: /api/ran/2410.02604.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
thuml/DARE canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
thuml/dare canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
AttentionModel Ran
ran on a synthesized input · constructed an object; no result was computed
thuml/dare/model/base_model_pytorch.py
pointer only (licence: NONE) · get_code("5f13f35abd14dc82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/dare when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BaseModel Ran
ran on a synthesized input · constructed an object; no result was computed
thuml/dare/model/base_model_pytorch.py
pointer only (licence: NONE) · get_code("aa3f1f6def5c6e54")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/dare when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

attention Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thuml/DARE/model/attention_pytorch.py
pointer only (licence: NONE) · get_code("b5459f1f6325b000")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/DARE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calc_auc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thuml/DARE/utils.py
pointer only (licence: NONE) · get_code("7873f0e1fa137cda")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/DARE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gauss_normalize Ran
ran, violated the contract we drafted
thuml/DARE/analysis/attention_accuracy_analysis/calc_learned.py
pointer only (licence: NONE) · get_code("f6dbcc7447051099")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/DARE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

min_max_normalize Ran
ran, violated the contract we drafted
thuml/DARE/analysis/attention_accuracy_analysis/calc_learned.py
pointer only (licence: NONE) · get_code("ef9170abf085609d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/DARE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalization Ran
ran, violated the contract we drafted
thuml/dare/analysis/attention_accuracy_analysis/calc_gt.py
pointer only (licence: NONE) · get_code("86c7147edb17dd5d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/dare when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_and_truncate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thuml/DARE/preprocess/taobao_v4.py
pointer only (licence: NONE) · get_code("9e51ba90ca7253fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/DARE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

softmax Ran
ran, violated the contract we drafted
thuml/DARE/analysis/attention_accuracy_analysis/calc_learned.py
pointer only (licence: NONE) · get_code("a585b44308980803")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thuml/DARE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
normalization 4 other papers
3 dated earlier, 1 later
2207.13325 (2022-07)
SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding
2306.09104 (2023-06)
On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation
2407.11633 (2024-07)
Scaling Diffusion Transformers to 16 Billion Parameters
and 1 more not named here
softmax 3 other papers
3 dated earlier
1908.09453 (2019-08)
OpenSpiel: A Framework for Reinforcement Learning in Games
2010.12777 (2020-10)
Improving Multilingual Models with Language-Clustered Vocabularies
2104.00795 (2021-04)
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Lifelong user behavior sequences are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle these long sequences: a subset of relevant behaviors is first searched from the original long sequences via an attention mechanism in the first stage and then aggregated with the target item to construct a discriminative representation for prediction in the second stage. In this work, we identify and characterize, for the first time, a neglected deficiency in existing long-sequence recommendation models: a single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes. Initial attempts to address this issue with some common methods (e.g., linear projections-a technique borrowed from language processing) proved ineffective, shedding light on the unique challenges of recommendation models. To overcome this, we propose the Decoupled Attention and Representation Embeddings (DARE) model, where two distinct embedding tables are initialized and learned separately to fully decouple attention and representation. Extensive experiments and analysis demonstrate that DARE provides more accurate searches of correlated behaviors and outperforms baselines with AUC gains up to 9‰ on public datasets and notable improvements on Tencent's advertising platform. Furthermore, decoupling embedding spaces allows us to reduce the attention embedding dimension and accelerate the search procedure by 50% without significant performance impact, enabling more efficient, high-performance online serving. Code in PyTorch for experiments, including model analysis, is available at https://github.com/thuml/DARE. ˚Equal contribution. Work was done while Ningya Feng and Baixu Chen were interns at Tencent. 1 In this paper, "attention" refers to attention scores-the softmax output that weights each behavior.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.02604")
get_code_for_paper("2410.02604")
have("2410.02604")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.02604.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.02604.svg)](https://syntology.ai/paper/2410.02604)

Connect an agent — have() is free.