SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.01265 · 2021

Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction

arXiv · PDF · Open in the Atlas

Code that ran

3 of 9 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 6 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/2108.01265.json · badge: /api/ran/2108.01265.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
fuyuanlyu/OptInter canonical (classifier label)
classifier basis: census
3 ran · 6 no recorded run
FunctionStatusWhere it lives
load_arch Ran
ran on a synthesized input
fuyuanlyu/OptInter/learn/utils.py
code served (permissive licence) · get_code("8cb7d5a42a010de5")
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 float, shape (2, 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
import tempfile
import os

# Create a temporary directory for our test file
temp_dir = tempfile.mkdtemp()

# Create a simple numpy array and save it
test_array = np.array([[1, 2, 3], [4, 5, 6]], dtype=np.float32)
model_path = os.path.join(temp_dir, "test_model.npy")
np.save(model_path, test_array)

ARGS = {
    "model_path": model_path
}
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 float, shape (2, 3) — shape (2, 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
read_data Ran
ran on a synthesized input
fuyuanlyu/OptInter/preprocess/utils.py
code served (permissive licence) · get_code("a2c3d1cc9f9b9ecc")
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 pandas as pd
import os
import tempfile
import shutil

# Create a temporary directory and test data file
temp_dir = tempfile.mkdtemp()
source_dir = temp_dir

# Create a sample train.txt file with tab-separated values
# Format: click \t cont_1 \t cont_2 \t ... \t cate_1 \t cate_2 \t ...
num_conts = 3
num_cates = 2
num_rows = 5

data_lines = []
for i in range(num_rows):
    click = i % 2  # 0 or 1
    conts = '\t'.join(str(float(j + i * 0.1)) for j in range(num_conts))
    cates = '\t'.join(str((j + i) % 5) for j in range(num_cates))
    line = f"{click}\t{conts}\t{cates}"
    data_lines.append(line)

train_file = os.path.join(source_dir, 'train.txt')
with open(train_file, 'w') as f:
    f.write('\n'.join(data_lines))

ARGS = {
    'source_dir': source_dir,
    'CONTS': num_conts,
    'CATES': num_cates,
    'name': 'train'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — 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
read_data Ran
ran on a synthesized input
fuyuanlyu/OptInter/learn/loader/Avazuloader.py
code served (permissive licence) · get_code("5620bdba80e2e81c")
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 tensorflow as tf
import numpy as np

SAMPLES = 1000
CATES = 24

# Create a valid TFRecord example serialized as bytes
def create_sample_tfrecord():
    # Create sample data
    label = np.random.rand(SAMPLES).astype(np.float32)
    feat_cates = np.random.randint(0, 100, size=SAMPLES * CATES, dtype=np.int64)
    
    # Create feature dict
    feature = {
        'label': tf.train.Feature(float_list=tf.train.FloatList(value=label)),
        'feat_cates': tf.train.Feature(int64_list=tf.train.Int64List(value=feat_cates))
    }
    
    # Create example and serialize
    example = tf.train.Example(features=tf.train.Features(feature=feature))
    return example.SerializeToString()

# Generate a sample raw record
raw_rec = create_sample_tfrecord()

ARGS = {
    'raw_rec': raw_rec
}
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 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
adjust_learning_rate Not yet run
unverified (harvested, no recorded run)
fuyuanlyu/OptInter/learn/AvazuTrain.py
code served (permissive licence) · get_code("067e7a974281c414")
How it ran

no invocation recorded.

count_parameters_in_GB Not yet run
unverified (harvested, no recorded run)
fuyuanlyu/OptInter/learn/utils.py
code served (permissive licence) · get_code("63aa1d8e45e966b0")
How it ran

no invocation recorded.

getmodel Not yet run
unverified (harvested, no recorded run)
fuyuanlyu/OptInter/learn/model/model.py
code served (permissive licence) · get_code("ef41f556ce32018e")
How it ran

no invocation recorded.

process_cate Not yet run
unverified (harvested, no recorded run)
fuyuanlyu/OptInter/preprocess/utils.py
code served (permissive licence) · get_code("fa15da1bc0b819c0")
How it ran

no invocation recorded.

process_cont Not yet run
unverified (harvested, no recorded run)
fuyuanlyu/OptInter/preprocess/utils.py
code served (permissive licence) · get_code("b0c4dfdeb480df6a")
How it ran

no invocation recorded.

read_data_comb Not yet run
unverified (harvested, no recorded run)
fuyuanlyu/OptInter/learn/loader/Avazuloader.py
code served (permissive licence) · get_code("10b06b1696ce85f7")
How it ran

no invocation 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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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.

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

Click-through rate prediction is one of the core tasks in commercial recommender systems. It aims to predict the probability of a user clicking a particular item given user and item features. As feature interactions bring in non-linearity, they are widely adopted to improve the performance of CTR prediction models. Therefore, effectively modelling feature interactions has attracted much attention in both the research and industry field. The current approaches can generally be categorized into three classes: (1) naïve methods, which do not model feature interactions and only use original features; (2) memorized methods, which memorize feature interactions by explicitly viewing them as new features and assigning trainable embeddings; (3) factorized methods, which learn latent vectors for original features and implicitly model feature interactions through factorization functions. Studies have shown that modelling feature interactions by one of these methods alone are suboptimal due to the unique characteristics of different feature interactions. To address this issue, we first propose a general framework called OptInter which finds the most suitable modelling method for each feature interaction. Different state-of-the-art deep CTR models can be viewed as instances of OptInter. To realize the functionality of OptInter, we also introduce a learning algorithm that automatically searches for the optimal modelling method. We conduct extensive experiments on four large datasets. Our experiments show that OptInter improves the best performed state-of-the-art baseline deep CTR models by up to 2.21%. Compared to the memorized method, which also outperforms baselines, we reduce up to 91% parameters. In addition, we conduct several ablation studies to investigate the influence of different components of OptInter. Finally, we provide interpretable discussions on the results of OptInter.

For agents

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

get_harvested_code_for_paper("2108.01265")
get_code_for_paper("2108.01265")
have("2108.01265")

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

curl https://syntology.ai/api/ran/2108.01265.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.01265.svg)](https://syntology.ai/paper/2108.01265)

Connect an agent — have() is free.