SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.04717 · 2019

Label Propagation for Deep Semi-supervised Learning

arXiv · PDF · Open in the Atlas

Code that ran

16 of 18 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; 4 honoured the contract we drafted, 3 violated it and 5 have no contract verdict; 4 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/1904.04717.json · badge: /api/ran/1904.04717.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
ahmetius/LP-DeepSSL canonical (classifier label)
classifier basis: census
16 ran · 2 no recorded run
FunctionStatusWhere it lives
sigmoid_rampup Ran
ran, honoured the contract we drafted
ahmetius/LP-DeepSSL/mean_teacher/ramps.py
code served (permissive licence) · get_code("3fb68ed6809a8085")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:27:05Z). 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

# The function sigmoid_rampup takes two parameters:
# - current: a numeric value representing the current step/epoch
# - rampup_length: a numeric value representing the total rampup length

ARGS = {
    "current": 5,
    "rampup_length": 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
ahmetius/LP-DeepSSL/mean_teacher/architectures.py
code served (permissive licence) · get_code("158bf4c3a5f11f04")
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) and returned Conv2d. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
cosine_rampdown Ran
ran, honoured the contract we drafted
ahmetius/LP-DeepSSL/mean_teacher/ramps.py
pointer only (licence: MIT); the stored copy get_code serves, from atinghosh/Adverserial-VAE, is pointer only (licence: NONE) · get_code("214e4ee9afcfa0e3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from atinghosh/Adverserial-VAE, and GitHub detected no licence in that repository 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.

export Ran
ran; our contract draft was wrong, not the code
ahmetius/LP-DeepSSL/mean_teacher/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from woriazzc/robust-pu, is pointer only (licence: NONE) · get_code("2660b9d52e1de712")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from woriazzc/robust-pu, and GitHub detected no licence in that repository 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.

has_file_allowed_extension Ran
ran, violated the contract we drafted
ahmetius/LP-DeepSSL/lp/db_semisuper.py
pointer only (licence: MIT); the stored copy get_code serves, from zhangyuanhan-ai/bamboo, is pointer only (licence: NONE) · get_code("c556c4f841693abe")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zhangyuanhan-ai/bamboo, and GitHub detected no licence in that repository 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.

is_image_file Ran
ran, violated the contract we drafted
ahmetius/LP-DeepSSL/lp/db_semisuper.py
code served (permissive licence) · get_code("f5510162ccebc03a")
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 bool, ndim 0, dtype family float, shape () 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 torch
import numpy as np

def has_file_allowed_extension(filename, extensions):
    """Checks if a file is an allowed extension.

    Args:
        filename (string): path to a file
        extensions (iterable of strings): extensions to consider (lowercase)

    Returns:
        bool: True if the filename ends with one of given extensions
    """
    filename_lower = filename.lower()
    return any((filename_lower.endswith(ext) for ext in extensions))

IMG_EXTENSIONS = ['.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif']

def is_image_file(filename):
    """Checks if a file is an allowed image extension.

    Args:
        filename (string): path to a file

    Returns:
        bool: True if the filename ends with a known image extension
    """
    return has_file_allowed_extension(filename, IMG_EXTENSIONS)

ARGS = {
    "filename": "photo.jpg"
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
iterate_eternally Ran
ran; our contract draft was wrong, not the code
ahmetius/LP-DeepSSL/mean_teacher/data.py
code served (permissive licence) · get_code("9e77e09f4d52e9da")
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 chain. 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 itertools
import numpy as np
import torch

# Set seed for reproducibility
np.random.seed(0)
torch.manual_seed(0)

# Construct arguments for iterate_eternally
# The function takes 'indices' as a parameter
# It uses np.random.permutation(indices), so indices should be array-like
# Looking at the function body:
# - indices is passed to np.random.permutation()
# - The result is yielded (so it should be iterable/indexable)

# Create a small indices array
indices = np.array([0, 1, 2, 3])

ARGS = {
    "indices": indices
}
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 chain — a chain output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a chain 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
iterate_once Ran
ran, violated the contract we drafted
ahmetius/LP-DeepSSL/mean_teacher/data.py
pointer only (licence: MIT); the stored copy get_code serves, from xujiaommcome/DiCo, is pointer only (licence: NONE) · get_code("4232c309adddf9e4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xujiaommcome/DiCo, and GitHub detected no licence in that repository 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.

linear_rampup Ran
ran, honoured the contract we drafted
ahmetius/LP-DeepSSL/mean_teacher/ramps.py
pointer only (licence: MIT); the stored copy get_code serves, from y-research-sbu/otsurv, is pointer only (licence: NOASSERTION) · get_code("069122bd5268cc56")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from y-research-sbu/otsurv, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

make_dataset Ran
ran; our contract draft was wrong, not the code
ahmetius/LP-DeepSSL/lp/db_semisuper.py
code served (permissive licence) · get_code("13d1069e836f8a7b")
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 list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()

# Create class subdirectories with some image files
class_dirs = ['class_a', 'class_b']
for class_name in class_dirs:
    class_path = os.path.join(temp_dir, class_name)
    os.makedirs(class_path, exist_ok=True)
    
    # Create some dummy image files
    for i in range(2):
        with open(os.path.join(class_path, f'image_{i}.jpg'), 'w') as f:
            f.write('dummy')
        with open(os.path.join(class_path, f'image_{i}.png'), 'w') as f:
            f.write('dummy')
    
    # Create a non-image file that should be ignored
    with open(os.path.join(class_path, 'readme.txt'), 'w') as f:
        f.write('dummy')

# Create mapping from class names to indices
class_to_idx = {'class_a': 0, 'class_b': 1}

# Define allowed image extensions
extensions = ('.jpg', '.jpeg', '.png', '.gif', '.bmp')

ARGS = {
    'dir': temp_dir,
    'class_to_idx': class_to_idx,
    'extensions': extensions
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
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
parameter_count Ran
ran, honoured the contract we drafted
ahmetius/LP-DeepSSL/mean_teacher/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from woriazzc/robust-pu, is pointer only (licence: NONE) · get_code("fd988895d0a19180")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from woriazzc/robust-pu, and GitHub detected no licence in that repository 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.

parameters_string Ran
ran on a synthesized input
ahmetius/LP-DeepSSL/mean_teacher/utils.py
code served (permissive licence) · get_code("cd6f95595f925d38")
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 torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
        self.conv1 = nn.Conv1d(2, 5, kernel_size=3)
    
    def forward(self, x):
        return x

module = SimpleModel()

ARGS = {
    'module': module
}
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 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
relabel_dataset Ran
ran on a synthesized input
ahmetius/LP-DeepSSL/mean_teacher/data.py
code served (permissive licence) · get_code("d8010fdbfbbbd4ce")
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 tuple. 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 os.path
import torch

NO_LABEL = -1

class MockDataset:
    def __init__(self):
        self.imgs = [
            ('/path/to/image1.jpg', 0),
            ('/path/to/image2.jpg', 1),
            ('/path/to/image3.jpg', 0),
            ('/path/to/image4.jpg', 1),
        ]
        self.all_labels = []
        self.p_labels = []
        self.labeled_idx = []
        self.unlabeled_idx = []
        self.class_to_idx = {
            'class_a': 0,
            'class_b': 1,
            'class_c': 2,
        }

dataset = MockDataset()

labels = {
    'image1.jpg': 'class_a',
    'image2.jpg': 'class_b',
    'image4.jpg': 'class_c',
}

ARGS = {
    'dataset': dataset,
    'labels': labels,
}
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 tuple — a tuple output has no array shape of its own; none is 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
softmax_kl_loss Ran
ran on a synthesized input
ahmetius/LP-DeepSSL/mean_teacher/losses.py
code served (permissive licence) · get_code("4b6074d01efc94cc")
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 Tensor, ndim 0, dtype family float, shape () 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for input and target logits
# Batch size: 2, Number of classes: 4
batch_size = 2
num_classes = 4

input_logits = torch.randn(batch_size, num_classes)
target_logits = torch.randn(batch_size, num_classes)

ARGS = {
    "input_logits": input_logits,
    "target_logits": target_logits,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
softmax_mse_loss Ran
ran on a synthesized input
ahmetius/LP-DeepSSL/mean_teacher/losses.py
code served (permissive licence) · get_code("160552ec3fea42de")
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 Tensor, ndim 0, dtype family float, shape () 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 torch
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create two small logit tensors with batch_size=2, num_classes=4
batch_size = 2
num_classes = 4

input_logits = torch.randn(batch_size, num_classes)
target_logits = torch.randn(batch_size, num_classes)

ARGS = {
    "input_logits": input_logits,
    "target_logits": target_logits,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
symmetric_mse_loss Ran
ran on a synthesized input
ahmetius/LP-DeepSSL/mean_teacher/losses.py
code served (permissive licence) · get_code("d75345cece6fcc81")
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 Tensor, ndim 0, dtype family float, shape () 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 torch

torch.manual_seed(0)

# Create two small tensors with the same shape
# batch_size=2, num_classes=4
input1 = torch.randn(2, 4, requires_grad=True)
input2 = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "input1": input1,
    "input2": input2,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
cg_diffusion Not yet run
unverified (harvested, no recorded run)
ahmetius/LP-DeepSSL/lp/diffusion.py
code served (permissive licence) · get_code("61ad799063fb382f")
How it ran

no invocation recorded.

normalize_connection_graph Not yet run
unverified (harvested, no recorded run)
ahmetius/LP-DeepSSL/lp/diffusion.py
code served (permissive licence) · get_code("64bb178d2364d65a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 14 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 14 later) and 4 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
conv1x1 431 other papers
27 dated earlier, 5 the same month, 398 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
sigmoid_rampup 19 other papers
1 dated earlier, 1 the same month, 17 later
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
1904.09058 (2019-04)
Feature Fusion for Online Mutual Knowledge Distillation
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
and 16 more not named here
has_file_allowed_extension 17 other papers
2 dated earlier, 15 later
1612.06321 (2016-12)
Large-Scale Image Retrieval with Attentive Deep Local Features
1902.02476 (2019-02)
A Simple Baseline for Bayesian Uncertainty in Deep Learning
1907.10830 (2019-07)
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
and 14 more not named here
linear_rampup 16 other papers
16 later
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
1911.08177 (2019-11)
Rethinking deep active learning: Using unlabeled data at model training
1912.09784 (2019-12)
Triple Generative Adversarial Networks
and 13 more not named here
cosine_rampdown 12 other papers
1 dated earlier, 11 later
1602.02644 (2016-02)
Generating Images with Perceptual Similarity Metrics based on Deep Networks
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
1911.08177 (2019-11)
Rethinking deep active learning: Using unlabeled data at model training
and 9 more not named here
is_image_file 11 other papers
2 dated earlier, 9 later
1812.10366 (2018-12)
A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images
1902.02476 (2019-02)
A Simple Baseline for Bayesian Uncertainty in Deep Learning
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
and 8 more not named here
iterate_once 10 other papers
10 later
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
1908.02983 (2019-08)
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
1911.08177 (2019-11)
Rethinking deep active learning: Using unlabeled data at model training
and 7 more not named here
iterate_eternally 9 other papers
9 later
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
1908.02983 (2019-08)
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
2003.09005 (2020-03)
Semi-Supervised Semantic Segmentation with Cross-Consistency Training
and 6 more not named here
export 6 other papers
6 later
2104.09459 (2021-04)
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
2106.06610 (2021-06)
Scalars are universal: Equivariant machine learning, structured like classical physics
2204.00887 (2022-04)
Dimensionless machine learning: Imposing exact units equivariance
and 3 more not named here
make_dataset 3 other papers
3 later
2003.08607 (2020-03)
Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
2302.11984 (2023-02)
Unsupervised Domain Adaptation via Distilled Discriminative Clustering
symmetric_mse_loss 2 other papers
2 later
2001.06001 (2020-01)
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
2006.11280 (2020-06)
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
cg_diffusion 1 other paper
1 later
1911.08177 (2019-11)
Rethinking deep active learning: Using unlabeled data at model training
parameter_count 1 other paper
1 later
2308.00279 (2023-08)
Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction
softmax_kl_loss 1 other paper
1 later
2006.11280 (2020-06)
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training

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

Semi-supervised learning is becoming increasingly important because it can combine data carefully labeled by humans with abundant unlabeled data to train deep neural networks. Classic methods on semi-supervised learning that have focused on transductive learning have not been fully exploited in the inductive framework followed by modern deep learning. The same holds for the manifold assumption---that similar examples should get the same prediction. In this work, we employ a transductive label propagation method that is based on the manifold assumption to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network. At the core of the transductive method lies a nearest neighbor graph of the dataset that we create based on the embeddings of the same network.Therefore our learning process iterates between these two steps. We improve performance on several datasets especially in the few labels regime and show that our work is complementary to current state of the art.

For agents

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

get_harvested_code_for_paper("1904.04717")
get_code_for_paper("1904.04717")
have("1904.04717")

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

curl https://syntology.ai/api/ran/1904.04717.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.04717.svg)](https://syntology.ai/paper/1904.04717)

Connect an agent — have() is free.