SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.00845 · NeurIPS · 2020

Addressing Target Shift in Zero-shot Learning using Grouped Adversarial Learning

Soumava Paul, Samarth Bharadwaj, Suranjana Samanta, Karthik Sankaranarayanan, Saneem Ahmed Chemmengath

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-21; 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/2003.00845.json · badge: /api/ran/2003.00845.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
mvp18/gAL-MELEX marked official in Papers with Code
Papers with Code archive
4 ran · 0 no recorded run
FunctionStatusWhere it lives
GAL Ran
ran on a synthesized input · constructed an object; no result was computed
mvp18/gAL-MELEX/APY/code/model.py
code served (permissive licence) · get_code("e828fbdd41054ac5")
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, GAL: 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 torch.nn as nn

torch.manual_seed(0)

# Define predicate groups for each group
predicate_groups = {
    'group1': ['pred_a', 'pred_b', 'pred_c'],
    'group2': ['pred_x', 'pred_y']
}

# Define the groups
groups = ['group1', 'group2']

# Define adversarial predicate groups
adv_predicate_groups = {
    'group1': ['adv_pred_a', 'adv_pred_b'],
    'group2': ['adv_pred_x', 'adv_pred_y', 'adv_pred_z']
}

# Define vector sizes: [backbone sizes, head/classifier sizes]
vector_size = [
    [2048, 512, 256],  # vsize[0]: backbone linear blocks
    [256, 128, 64]     # vsize[1]: LSA backbone and group heads
]

# Define adversarial dictionary
adv_dict = [
    {'node_name': 'adv_branch1', 'group': 'group1'},
    {'node_name': 'adv_branch2', 'group': 'group2'}
]

# Define loss weights
loss_weights = {
    'main': 1.0,
    'adv': 0.5
}

ARGS = {
    'predicate_groups': predicate_groups,
    'groups': groups,
    'adv_predicate_groups': adv_predicate_groups,
    'vector_size': vector_size,
    'proj_version': 0,
    'ec': 0,
    'adv_dict': adv_dict,
    'loss_weights': loss_weights,
    'zero_shot': 0,
    'drop_rate': 0.1,
    'add_relu': True
}
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 GAL — 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 GAL 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
GradReverse Ran
ran on a synthesized input · constructed an object; no result was computed
mvp18/gAL-MELEX/APY/code/model.py
code served (permissive licence) · get_code("5a9a5eb577f20e70")
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, GradReverse: 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
from torch.autograd import Function

torch.manual_seed(0)

class GradReverse(Function):

    @staticmethod
    def forward(ctx, x, lambda_):
        ctx.lambda_ = lambda_
        return x.view_as(x)

    @staticmethod
    def backward(ctx, grad_output):
        reversed_scaled_grad = torch.neg(ctx.lambda_ * grad_output.clone())
        return (reversed_scaled_grad, None)


# Create arguments for GradReverse
x = torch.randn(2, 4, requires_grad=True)
lambda_ = 0.5

ARGS = {
    "x": x,
    "lambda_": lambda_
}
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 GradReverse — 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 GradReverse 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
Merge Ran
ran; our contract draft was wrong, not the code
mvp18/gAL-MELEX/APY/code/model.py
code served (permissive licence) · get_code("2599ba4db1567616")
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

torch.manual_seed(0)

# Merge function takes two dictionaries and merges them
# dict1 and dict2 should be dictionaries with any content

dict1 = {
    "key1": "value1",
    "key2": 42,
    "tensor1": torch.randn(2, 4)
}

dict2 = {
    "key3": "value3",
    "key4": 3.14,
    "tensor2": torch.randn(3, 4)
}

ARGS = {
    "dict1": dict1,
    "dict2": dict2
}
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
grad_reverse Ran
ran, honoured the contract we drafted
mvp18/gAL-MELEX/APY/code/model.py
code served (permissive licence) · get_code("5a2b24f39d01d817")
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

torch.manual_seed(0)

# Create a small tensor for x
x = torch.randn(2, 4, requires_grad=True)

# Create a scalar lambda value
LAMBDA = 0.5

ARGS = {
    "x": x,
    "LAMBDA": LAMBDA
}
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

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Zero-shot learning (ZSL) algorithms typically work by exploiting attribute correlations to be able to make predictions in unseen classes. However, these correlations do not remain intact at test time in most practical settings and the resulting change in these correlations lead to adverse effects on zero-shot learning performance. In this paper, we present a new paradigm for ZSL that: (i) utilizes the class-attribute mapping of unseen classes to estimate the change in target distribution (target shift), and (ii) propose a novel technique called grouped Adversarial Learning (gAL) to reduce negative effects of this shift. Our approach is widely applicable for several existing ZSL algorithms, including those with implicit attribute predictions. We apply the proposed technique (gAL) on three popular ZSL algorithms: ALE, SJE, and DEVISE, and show performance improvements on 4 popular ZSL datasets: AwA2, aPY, CUB and SUN. We obtain SOTA results on SUN and aPY datasets and achieve comparable results on AwA2.

For agents

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

get_harvested_code_for_paper("2003.00845")
get_code_for_paper("2003.00845")
have("2003.00845")

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

curl https://syntology.ai/api/ran/2003.00845.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.00845.svg)](https://syntology.ai/paper/2003.00845)

Connect an agent — have() is free.