SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.09433 · 2019

FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

arXiv · PDF · Open in the Atlas

Code that ran

12 of 26 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; 2 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 0 failures of our instrument; 14 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/1905.09433.json · badge: /api/ran/1905.09433.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
datawhalechina/torch-rechub community (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
DataCanvasIO/DeepTables community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
tangxyw/RecAlgorithm community (classifier label)
classifier basis not recorded on the link
2 ran · 10 no recorded run
codectr/RefineCTR extension (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
huangjunheng/recommendation_model reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
activation_layer Ran
ran on a synthesized input
datawhalechina/torch-rechub/torch_rechub/basic/activation.py
code served (permissive licence) · get_code("b9cfbe7def435449")
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 Sigmoid. 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):
    """The Dice activation function mentioned in the `DIN paper
    https://arxiv.org/abs/1706.06978`
    """

    def __init__(self, epsilon=0.001):
        super(Dice, self).__init__()
        self.epsilon = epsilon
        self.alpha = nn.Parameter(torch.randn(1))

    def forward(self, x: torch.Tensor):
        avg = x.mean(dim=1)
        avg = avg.unsqueeze(dim=1)
        var = torch.pow(x - avg, 2) + self.epsilon
        var = var.sum(dim=1).unsqueeze(dim=1)
        ps = (x - avg) / torch.sqrt(var)
        ps = nn.Sigmoid()(ps)
        return ps * x + (1 - ps) * self.alpha * x

def activation_layer(act_name):
    """Construct activation layers

    Args:
        act_name: str or nn.Module, name of activation function

    Returns:
        act_layer: activation layer
    """
    if isinstance(act_name, str):
        if act_name.lower() == 'sigmoid':
            act_layer = nn.Sigmoid()
        elif act_name.lower() == 'relu':
            act_layer = nn.ReLU(inplace=True)
        elif act_name.lower() == 'dice':
            act_layer = Dice()
        elif act_name.lower() == 'prelu':
            act_layer = nn.PReLU()
        elif act_name.lower() == 'softmax':
            act_layer = nn.Softmax(dim=1)
        elif act_name.lower() == 'leakyrelu':
            act_layer = nn.LeakyReLU()
    elif issubclass(act_name, nn.Module):
        act_layer = act_name()
    else:
        raise NotImplementedError
    return act_layer

ARGS = {
    "act_name": "sigmoid"
}
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 Sigmoid — a Sigmoid output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sigmoid 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
auc_score Ran
ran on a synthesized input
datawhalechina/torch-rechub/torch_rechub/basic/metric.py
code served (permissive licence) · get_code("f595ec56e4f6d96c")
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 float, 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
from sklearn.metrics import roc_auc_score

torch.manual_seed(0)

# Create valid arguments for auc_score function
# The function expects y_true and y_pred to be array-like objects
# suitable for sklearn's roc_auc_score

# y_true: binary labels (0 or 1)
y_true = np.array([0, 1, 1, 0, 1, 0])

# y_pred: predicted probabilities or scores (values between 0 and 1)
y_pred = np.array([0.1, 0.9, 0.8, 0.2, 0.7, 0.3])

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — 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
count_params Ran
ran, honoured the contract we drafted
codectr/RefineCTR/evaluation/mains/main_criteo_base.py
pointer only (licence: NONE) · get_code("c7366824116a54de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, codectr/RefineCTR 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.

extract_feature_info Ran
ran on a synthesized input
datawhalechina/torch-rechub/torch_rechub/utils/model_utils.py
code served (permissive licence) · get_code("b05d0a65616555c4")
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 dict. 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 Feature:
    """Stand-in Feature class with name attribute."""
    def __init__(self, name):
        self.name = name

class MockRechubModel(nn.Module):
    """Minimal torch-rechub model with feature attributes."""
    def __init__(self):
        super().__init__()
        self.user_id_feat = Feature("user_id")
        self.item_id_feat = Feature("item_id")
        self.user_age_feat = Feature("user_age")
        self.item_price_feat = Feature("item_price")
        
        self.features = [self.user_id_feat, self.item_id_feat]
        self.deep_features = [self.user_age_feat, self.item_price_feat]
        self.user_features = [self.user_id_feat, self.user_age_feat]
        self.item_features = [self.item_id_feat, self.item_price_feat]
        
        self.linear = nn.Linear(4, 1)
    
    def forward(self, x):
        return self.linear(x)

model = MockRechubModel()

ARGS = {
    "model": model,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
gauc_score Ran
ran on a synthesized input
datawhalechina/torch-rechub/torch_rechub/basic/metric.py
code served (permissive licence) · get_code("8a2d833b56e533eb")
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 float, 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 numpy as np

# Construct valid arguments for gauc_score function
np.random.seed(0)

# Create sample data
n_samples = 8
y_true = np.array([1, 0, 1, 1, 0, 1, 0, 0], dtype=int)
y_pred = np.array([0.9, 0.2, 0.8, 0.7, 0.3, 0.85, 0.1, 0.15], dtype=float)
users = np.array([1, 1, 2, 2, 3, 3, 3, 4], dtype=int)

# Optional weights dict (None means use count as weight)
weights = None

# Alternative: create weights dict
# weights = {1: 2, 2: 2, 3: 3, 4: 1}

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
    'users': users,
    'weights': weights
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
get_user_pred Ran
ran on a synthesized input
datawhalechina/torch-rechub/torch_rechub/basic/metric.py
code served (permissive licence) · get_code("073e23c27ccb1369")
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 dict. 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

torch.manual_seed(0)

# Create small test data
y_true = np.array([1, 0, 1, 0, 1])
y_pred = np.array([0.9, 0.1, 0.8, 0.2, 0.7])
users = np.array([101, 102, 101, 103, 102])

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
    'users': users
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
leakyrelu Ran
ran on a synthesized input
tangxyw/RecAlgorithm/algorithm/BST/leakyrelu.py
code served (permissive licence) · get_code("a454c87f745b2bc3")
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 EagerTensor, ndim 2, dtype family float, 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 tensorflow as tf
import numpy as np

# Create a small TensorFlow tensor for testing
x = tf.constant([[-1.0, -0.5, 0.5, 1.0],
                  [2.0, -2.0, 0.0, -0.1]], dtype=tf.float32)

# Define leak parameter
leak = 0.01

# Construct ARGS dictionary with all parameters
ARGS = {
    "x": x,
    "leak": leak
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, 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
mini_dt_space_validator Ran
ran on a synthesized input
DataCanvasIO/DeepTables/deeptables/models/hyper_dt.py
code served (permissive licence) · get_code("acec900be1840259")
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 torch.nn as nn

torch.manual_seed(0)

class Param:
    def __init__(self, alias, value):
        self.alias = alias
        self.value = value

class Sample:
    def __init__(self, params):
        self.params = params
    
    def get_assigned_params(self):
        return self.params

# Create sample with params that have .nets alias
param1 = Param("model.nets", ["fm_nets"])
param2 = Param("other.value", 42)

sample = Sample([param1, param2])

ARGS = {
    "sample": sample
}
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 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
target_rate_encodeing Ran
ran on a synthesized input
DataCanvasIO/DeepTables/deeptables/preprocessing/utils.py
code served (permissive licence) · get_code("24e398d27e643ab0")
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 DataFrame. 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 pandas as pd
import numpy as np

# Create a simple dataframe with categorical features and a binary target
np.random.seed(0)

# Create sample data
n_rows = 10
df = pd.DataFrame({
    'feature1': ['A', 'B', 'A', 'C', 'B', 'A', 'C', 'B', 'A', 'C'],
    'feature2': ['X', 'Y', 'X', 'Z', 'Y', 'X', 'Z', 'Y', 'X', 'Z'],
    'target': [0, 1, 0, 1, 1, 0, 1, 0, 1, 1]
})

# Define arguments
ARGS = {
    'feat_to_encode': ['feature1', 'feature2'],
    'target': 'target',
    'df': df.copy(),
    'mode': 'order'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
to_sparse_tensor Ran
ran on a synthesized input
tangxyw/RecAlgorithm/algorithm/utils.py
code served (permissive licence) · get_code("edc3a0e6c82606b3")
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 SparseTensor. 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 tensorflow as tf
import numpy as np

# Create a small one-hot/multi-hot tensor
# Shape: (2, 4) - batch size 2, 4 features
one_hot_tensor = tf.constant([
    [1, 0, 1, 0],
    [0, 1, 0, 1]
], dtype=tf.int32)

ARGS = {
    "one_hot_tensor": one_hot_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SparseTensor — a SparseTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SparseTensor 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
top_categories Ran
ran on a synthesized input
DataCanvasIO/DeepTables/deeptables/eda/utils.py
code served (permissive licence) · get_code("a472efb327506298")
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 Index. 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 pandas as pd
import numpy as np

# Create a small DataFrame with a category feature
data = {
    'category_feature': ['A', 'B', 'A', 'C', 'B', 'A', 'D', 'E', 'A', 'B', 'C', 'A'],
    'other_col': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
}
df = pd.DataFrame(data)

ARGS = {
    'df': df,
    'category_feature': 'category_feature',
    'topN': 30
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Index — a Index output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Index output the recorded ndim 1 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
train Ran
ran, honoured the contract we drafted
codectr/RefineCTR/evaluation/mains/main_criteo_base.py
pointer only (licence: NONE) · get_code("e2dddebbea9ec26d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, codectr/RefineCTR 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.

afm_model_fn Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/AFM/afm.py
code served (permissive licence) · get_code("c0a4eb57bcd0b82c")
How it ran

no invocation recorded.

bidirectional_dynamic_rnn Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/DIEN/rnn.py
code served (permissive licence) · get_code("655674e1dd763c2b")
How it ran

no invocation recorded.

columns_info Not yet run
unverified (harvested, no recorded run)
DataCanvasIO/DeepTables/deeptables/eda/utils.py
code served (permissive licence) · get_code("8d782cde176050f5")
How it ran

no invocation recorded.

cross_layer Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/DCN/cross_layer.py
code served (permissive licence) · get_code("6ab7bf854f4e2b6a")
How it ran

no invocation recorded.

dice Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/DIN/activations.py
code served (permissive licence) · get_code("cf507ada9edcace1")
How it ran

no invocation recorded.

dynamic_rnn Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/DIEN/rnn.py
code served (permissive licence) · get_code("e9998a77e293fcee")
How it ran

no invocation recorded.

eval_input_fn Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/utils.py
code served (permissive licence) · get_code("cffd7b17cdcd0cf1")
How it ran

no invocation recorded.

example_parser Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/AFM/afm.py
code served (permissive licence) · get_code("e123b326d5597e1a")
How it ran

no invocation recorded.

generate_dummy_input Not yet run
unverified (harvested, no recorded run)
datawhalechina/torch-rechub/torch_rechub/utils/model_utils.py
code served (permissive licence) · get_code("39e31791691af4ad")
How it ran

no invocation recorded.

generate_dummy_input_dict Not yet run
unverified (harvested, no recorded run)
datawhalechina/torch-rechub/torch_rechub/utils/model_utils.py
code served (permissive licence) · get_code("bd1115d11db962ea")
How it ran

no invocation recorded.

get_auc Not yet run
unverified (harvested, no recorded run)
huangjunheng/recommendation_model/FiBiNET/FibiNET.py
pointer only (licence: NONE) · get_code("d1f034d725053a85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, huangjunheng/recommendation_model 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. No invocation recorded.

prelu Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/DIN/activations.py
code served (permissive licence) · get_code("3e2819d0a6e96a88")
How it ran

no invocation recorded.

raw_rnn Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/DIEN/rnn.py
code served (permissive licence) · get_code("d657922c4bdcd359")
How it ran

no invocation recorded.

train_input_fn Not yet run
unverified (harvested, no recorded run)
tangxyw/RecAlgorithm/algorithm/utils.py
code served (permissive licence) · get_code("35705e483fa1b7a1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 26 samples lifted from this paper's linked repositories, 26 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 22 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
bidirectional_dynamic_rnn 1 other paper
1 later
2006.15408 (2020-06)
Learning Optimal Tree Models under Beam Search
count_params 1 other paper
1 later
2204.08758 (2022-04)
Enhancing CTR Prediction with Context-Aware Feature Representation Learning
dynamic_rnn 1 other paper
1 later
2006.15408 (2020-06)
Learning Optimal Tree Models under Beam Search
raw_rnn 1 other paper
1 later
2006.15408 (2020-06)
Learning Optimal Tree Models under Beam Search

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

More are linked than shown here.

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

Abstract

Advertising and feed ranking are essential to many Internet companies such as Facebook and Sina Weibo. Among many real-world advertising and feed ranking systems, click through rate (CTR) prediction plays a central role. There are many proposed models in this field such as logistic regression, tree based models, factorization machine based models and deep learning based CTR models. However, many current works calculate the feature interactions in a simple way such as Hadamard product and inner product and they care less about the importance of features. In this paper, a new model named FiBiNET as an abbreviation for Feature Importance and Bilinear feature Interaction NETwork is proposed to dynamically learn the feature importance and fine-grained feature interactions. On the one hand, the FiBiNET can dynamically learn the importance of features via the Squeeze-Excitation network (SENET) mechanism; on the other hand, it is able to effectively learn the feature interactions via bilinear function. We conduct extensive experiments on two real-world datasets and show that our shallow model outperforms other shallow models such as factorization machine(FM) and field-aware factorization machine(FFM). In order to improve performance further, we combine a classical deep neural network(DNN) component with the shallow model to be a deep model. The deep FiBiNET consistently outperforms the other state-of-the-art deep models such as DeepFM and extreme deep factorization machine(XdeepFM).

For agents

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

get_harvested_code_for_paper("1905.09433")
get_code_for_paper("1905.09433")
have("1905.09433")

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

curl https://syntology.ai/api/ran/1905.09433.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.09433.svg)](https://syntology.ai/paper/1905.09433)

Connect an agent — have() is free.