SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.14652 · ICCV · 2023

Invariant Feature Regularization for Fair Face Recognition

Hanwang Zhang, Zhongqi Yue, Sugiri Pranata, Karlekar Jayashree, Jiali Ma, Kagaya Tomoyuki, Suzuki Tomoki

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 1 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/2310.14652.json · badge: /api/ran/2310.14652.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
panasonicconnect/invreg marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
AllGather Ran
ran on a synthesized input
panasonicconnect/invreg/utils/utils_invreg.py
code served (permissive licence) · get_code("1736503522b025e1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple, ndim 3, 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 torch
import torch.distributed as dist
import os
import tempfile

# Set up a minimal single-process distributed environment
os.environ['MASTER_ADDR'] = 'localhost'
os.environ['MASTER_PORT'] = '29500'
os.environ['RANK'] = '0'
os.environ['WORLD_SIZE'] = '1'

# Initialize process group
if not dist.is_initialized():
    dist.init_process_group(backend='gloo', rank=0, world_size=1)

INIT_ARGS = {}

ARGS = {
    'input': torch.randn(3, 5)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
DistAllGather Ran
ran on a synthesized input · constructed an object; no result was computed
panasonicconnect/invreg/utils/utils_invreg.py
code served (permissive licence) · get_code("3ab310efaf89176b")
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, DistAllGather: the run constructed the object and did not call it, so no result was computed. 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 os

torch.manual_seed(0)

# Set up distributed environment variables
os.environ['WORLD_SIZE'] = '2'
os.environ['RANK'] = '0'
os.environ['MASTER_ADDR'] = 'localhost'
os.environ['MASTER_PORT'] = '29500'

# Initialize distributed process group (single process simulation)
# For CPU-only testing, we use the 'gloo' backend
try:
    if not torch.distributed.is_initialized():
        torch.distributed.init_process_group(
            backend='gloo',
            rank=0,
            world_size=1  # Single process, so world_size is 1
        )
except RuntimeError:
    pass

# Create a small input tensor for the function
# The function expects a tensor as input
input_tensor = torch.randn(2, 4, requires_grad=True)

ARGS = {
    'input': input_tensor
}
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 DistAllGather — 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 DistAllGather 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
all_reduce Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
panasonicconnect/invreg/utils/utils_invreg.py
code served (permissive licence) · get_code("6a8ca1053b179d97")
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 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 torch
import os
import torch.distributed as dist
from unittest.mock import MagicMock, patch

torch.manual_seed(0)

# Set up minimal distributed environment variables
os.environ['WORLD_SIZE'] = '1'
os.environ['RANK'] = '0'
os.environ['MASTER_ADDR'] = 'localhost'
os.environ['MASTER_PORT'] = '29500'

# Mock the distributed functions since we're running single-process
original_all_gather = dist.all_gather
original_reduce_scatter = dist.reduce_scatter
original_barrier = dist.barrier

def mock_all_gather(gather_list, input_tensor, group=None):
    """Mock all_gather that just puts input in first position"""
    gather_list[0] = input_tensor

def mock_reduce_scatter(output, input_list, group=None):
    """Mock reduce_scatter that sums inputs into output"""
    result = torch.zeros_like(output)
    for tensor in input_list:
        result = result + tensor
    output.copy_(result)

def mock_barrier():
    """Mock barrier - no-op"""
    pass

# Patch distributed functions
dist.all_gather = mock_all_gather
dist.reduce_scatter = mock_reduce_scatter
dist.barrier = mock_barrier

# Create a small tensor to pass to all_reduce
tensor = torch.randn(2, 4)

ARGS = {
    'tensor': tensor
}
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 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
env_loss_ce_ddp Not yet run
unverified (harvested, no recorded run)
panasonicconnect/invreg/utils/utils_invreg.py
code served (permissive licence) · get_code("7bb0c00f22d2ba09")
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, 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 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.

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

Fair face recognition is all about learning invariant feature that generalizes to unseen faces in any demographic group. Unfortunately, face datasets inevitably capture the imbalanced demographic attributes that are ubiquitous in real-world observations, and the model learns biased feature that generalizes poorly in the minority group. We point out that the bias arises due to the confounding demographic attributes, which mislead the model to capture the spurious demographic-specific feature. The confounding effect can only be removed by causal intervention, which requires the confounder annotations. However, such annotations can be prohibitively expensive due to the diversity of the demographic attributes. To tackle this, we propose to generate diverse data partitions iteratively in an unsupervised fashion. Each data partition acts as a self-annotated confounder, enabling our Invariant Feature Regularization (INV-REG) to deconfound. INV-REG is orthogonal to existing methods, and combining INV-REG with two strong baselines (Arcface and CIFP) leads to new state-of-the-art that improves face recognition on a variety of demographic groups. Code is available at https://github.com/milliema/InvReg.

For agents

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

get_harvested_code_for_paper("2310.14652")
get_code_for_paper("2310.14652")
have("2310.14652")

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

curl https://syntology.ai/api/ran/2310.14652.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.14652.svg)](https://syntology.ai/paper/2310.14652)

Connect an agent — have() is free.