SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.04746 · IJCAI · 2024

SVD-AE: Simple Autoencoders for Collaborative Filtering

Noseong Park, Jeongwhan Choi, Seoyoung Hong, Srijan Kumar, Yeon-Chang Lee

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has 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/2405.04746.json · badge: /api/ran/2405.04746.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
seoyoungh/svd-ae canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
jeongwhanchoi/svd-ae marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
SVD_AE Ran
ran on a synthesized input · constructed an object; no result was computed
jeongwhanchoi/svd-ae/model.py
code served (permissive licence) · get_code("4cbb20e7cb8dc4e4")
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 an instance of its own class, SVD_AE: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from torch import nn

torch.manual_seed(0)

# Create small sparse adjacency matrix (4x3 for distinctness)
adj_mat = torch.sparse_coo_tensor(
    indices=torch.tensor([[0, 1, 2, 3], [0, 1, 2, 0]]),
    values=torch.tensor([1.0, 1.0, 1.0, 1.0]),
    size=(4, 3)
)

# Create small dense normalized adjacency matrix (4x4)
norm_adj = torch.eye(4)

# User singular vectors (4x2)
user_sv = torch.randn(4, 2)

# Item singular vectors (3x2)
item_sv = torch.randn(3, 2)

ARGS = {
    'adj_mat': adj_mat,
    'norm_adj': norm_adj,
    'user_sv': user_sv,
    'item_sv': item_sv,
    'device': 'cpu'
}
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 SVD_AE — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SVD_AE 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
get_common_path Ran
ran; our contract draft was wrong, not the code
seoyoungh/svd-ae/utils.py
code served (permissive licence) · get_code("efee3bbbbd59ab7d")
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 str. 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 numpy as np

ARGS = {
    'hyper_params': {
        'dataset': 'mnist',
        'model': 'svd-ae',
        'k': 10,
        'grid_search_lamda': False,
        'lamda': 0.001,
        'seed': 42
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_item_propensity Ran
ran, honoured the contract we drafted
seoyoungh/svd-ae/utils.py
code served (permissive licence) · get_code("39c4594180be0c7c")
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 1, dtype family float, shape (3,) 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
from collections import defaultdict

class MockData:
    def __init__(self):
        self.data = {
            'train': [
                (0, 0, 5),
                (1, 1, 4),
                (2, 0, 3),
                (3, 2, 5),
                (4, 1, 2),
            ]
        }

hyper_params = {
    'num_items': 3,
    'num_interactions': 5
}

data = MockData()

ARGS = {
    'hyper_params': hyper_params,
    'data': data,
    'A': 0.55,
    'B': 1.5
}
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 1, dtype family float, shape (3,) — shape (3,) 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
get_item_count_map Not yet run
unverified (harvested, no recorded run)
seoyoungh/svd-ae/utils.py
code served (permissive licence) · get_code("dc1e506d9e302f57")
How it ran

no invocation recorded.

load_raw_dataset Not yet run
unverified (harvested, no recorded run)
seoyoungh/svd-ae/data.py
code served (permissive licence) · get_code("55ab6b432bbbdc36")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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, 0 later) and 3 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
get_item_count_map 1 other paper
1 dated earlier
2206.02626 (2022-06)
Infinite Recommendation Networks: A Data-Centric Approach
get_item_propensity 1 other paper
1 dated earlier
2206.02626 (2022-06)
Infinite Recommendation Networks: A Data-Centric Approach

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

Collaborative filtering (CF) methods for recommendation systems have been extensively researched, ranging from matrix factorization and autoencoder-based to graph filtering-based methods. Recently, lightweight methods that require almost no training have been recently proposed to reduce overall computation. However, existing methods still have room to improve the trade-offs among accuracy, efficiency, and robustness. In particular, there are no well-designed closed-form studies for balanced CF in terms of the aforementioned tradeoffs. In this paper, we design SVD-AE, a simple yet effective singular vector decomposition (SVD)based linear autoencoder, whose closed-form solution can be defined based on SVD for CF. SVD-AE does not require iterative training processes as its closed-form solution can be calculated at once. Furthermore, given the noisy nature of the rating matrix, we explore the robustness against such noisy interactions of existing CF methods and our SVD-AE. As a result, we demonstrate that our simple design choice based on truncated SVD can be used to strengthen the noise robustness of the recommendation while improving efficiency. Code is available at https://github.com/seoyoungh/svd-ae.

For agents

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

get_harvested_code_for_paper("2405.04746")
get_code_for_paper("2405.04746")
have("2405.04746")

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

curl https://syntology.ai/api/ran/2405.04746.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.04746.svg)](https://syntology.ai/paper/2405.04746)

Connect an agent — have() is free.