SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.15635 · 2024

RecDCL: Dual Contrastive Learning for Recommendation

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 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/2401.15635.json · badge: /api/ran/2401.15635.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
thudm/recdcl canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
activation_layer Ran
ran; our contract draft was wrong, not the code
thudm/recdcl/recbole/model/layers.py
code served (permissive licence) · get_code("b5b0bb176f34b7a4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ReLU. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class Dice(nn.Module):
    """Dice activation function

    .. math::
        f(s)=p(s) \\cdot s+(1-p(s)) \\cdot \\alpha s

    .. math::
        p(s)=\\frac{1} {1 + e^{-\\frac{s-E[s]} {\\sqrt {Var[s] + \\epsilon}}}}
    """

    def __init__(self, emb_size):
        super(Dice, self).__init__()
        self.sigmoid = nn.Sigmoid()
        self.alpha = torch.zeros((emb_size,))

    def forward(self, score):
        self.alpha = self.alpha.to(score.device)
        score_p = self.sigmoid(score)
        return self.alpha * (1 - score_p) * score + score_p * score

def activation_layer(activation_name='relu', emb_dim=None):
    """Construct activation layers

    Args:
        activation_name: str, name of activation function
        emb_dim: int, used for Dice activation

    Return:
        activation: activation layer
    """
    if activation_name is None:
        activation = None
    elif isinstance(activation_name, str):
        if activation_name.lower() == 'sigmoid':
            activation = nn.Sigmoid()
        elif activation_name.lower() == 'tanh':
            activation = nn.Tanh()
        elif activation_name.lower() == 'relu':
            activation = nn.ReLU()
        elif activation_name.lower() == 'leakyrelu':
            activation = nn.LeakyReLU()
        elif activation_name.lower() == 'dice':
            activation = Dice(emb_dim)
        elif activation_name.lower() == 'none':
            activation = None
    elif issubclass(activation_name, nn.Module):
        activation = activation_name()
    else:
        raise NotImplementedError('activation function {} is not implemented'.format(activation_name))
    return activation

ARGS = {
    'activation_name': 'relu',
    'emb_dim': 8
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
hit_ Ran
ran, honoured the contract we drafted
thudm/recdcl/recbole/evaluator/metrics.py
code served (permissive licence) · get_code("83ba6af9d18dc931")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct arguments for hit_ function
# The function takes pos_index (array-like) and pos_len (used in docstring but not in actual code)
# pos_index should be a 2D array where rows are batches and columns are ranked items
# Each element indicates whether that position is a hit (positive sample)

pos_index = np.array([
    [1, 0, 0, 1],
    [0, 1, 0, 0]
], dtype=int)

pos_len = 4

ARGS = {
    "pos_index": pos_index,
    "pos_len": pos_len
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
map_ Not yet run
unverified (harvested, no recorded run)
thudm/recdcl/recbole/evaluator/metrics.py
code served (permissive licence) · get_code("b789b2a14dd19e0c")
How it ran

no invocation recorded.

mrr_ Not yet run
unverified (harvested, no recorded run)
thudm/recdcl/recbole/evaluator/metrics.py
code served (permissive licence) · get_code("a7dd48dfe868e2d3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 2 later) and 0 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
activation_layer 18 other papers
9 dated earlier, 1 the same month, 8 later
2110.05730 (2021-10)
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
2204.11046 (2022-04)
Decoupled Side Information Fusion for Sequential Recommendation
2205.08776 (2022-05)
AdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation
and 15 more not named here
hit_ 4 other papers
3 dated earlier, 1 later
2110.05730 (2021-10)
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
2206.12811 (2022-06)
Towards Representation Alignment and Uniformity in Collaborative Filtering
2304.09184 (2023-04)
Frequency Enhanced Hybrid Attention Network for Sequential Recommendation
and 1 more not named here
map_ 3 other papers
3 dated earlier
2110.05730 (2021-10)
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
2206.12811 (2022-06)
Towards Representation Alignment and Uniformity in Collaborative Filtering
2304.09184 (2023-04)
Frequency Enhanced Hybrid Attention Network for Sequential Recommendation
mrr_ 3 other papers
3 dated earlier
2110.05730 (2021-10)
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
2206.12811 (2022-06)
Towards Representation Alignment and Uniformity in Collaborative Filtering
2304.09184 (2023-04)
Frequency Enhanced Hybrid Attention Network for Sequential Recommendation

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

Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by contrasting the embeddings between raw and augmented data. However, existing CL-based methods mostly focus on contrasting in a batch-wise way, failing to exploit potential regularity in the feature dimension. This leads to redundant solutions during the representation learning of users and items. In this work, we investigate how to employ both batch-wise CL (BCL) and feature-wise CL (FCL) for recommendation. We theoretically analyze the relation between BCL and FCL, and find that combining BCL and FCL helps eliminate redundant solutions but never misses an optimal solution. We propose a dual contrastive learning recommendation framework -- RecDCL. In RecDCL, the FCL objective is designed to eliminate redundant solutions on user-item positive pairs and to optimize the uniform distributions within users and items using a polynomial kernel for driving the representations to be orthogonal; The BCL objective is utilized to generate contrastive embeddings on output vectors for enhancing the robustness of the representations. Extensive experiments on four widely-used benchmarks and one industry dataset demonstrate that RecDCL can consistently outperform the state-of-the-art GNNs-based and SSL-based models (with an improvement of up to 5.65\% in terms of Recall@20). The source code is publicly available (https://github.com/THUDM/RecDCL).

For agents

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

get_harvested_code_for_paper("2401.15635")
get_code_for_paper("2401.15635")
have("2401.15635")

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

curl https://syntology.ai/api/ran/2401.15635.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.15635.svg)](https://syntology.ai/paper/2401.15635)

Connect an agent — have() is free.