SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.13853 · ICML · 2025

AutoAL: Automated Active Learning with Differentiable Query Strategy Search

Yifeng Wang, Xueying Zhan, Siyu Huang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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 1 has no contract verdict; 2 failures of our instrument; 2 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/2410.13853.json · badge: /api/ran/2410.13853.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
haizailache999/AutoAL canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
haizailache999/autoal canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Architect Ran
ran on a synthesized input · constructed an object; no result was computed
haizailache999/autoal/AL_model.py
code served (permissive licence) · get_code("942f2b4d59e0270f")
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, Architect: 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
import torch.nn.functional as F
import math

torch.manual_seed(0)

# Define a minimal model that has named parameters with and without '_1' in the name
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.layer_1 = nn.Linear(4, 3)
        self.layer_2 = nn.Linear(3, 4)
    
    def forward(self, x):
        return self.layer_2(self.layer_1(x))

# Define a minimal loss module that takes output_feature as input
class LossModule(nn.Module):
    def __init__(self):
        super(LossModule, self).__init__()
        self.fc = nn.Linear(4, 1)
    
    def forward(self, x):
        return self.fc(x)

# Create instances
model = SimpleModel()
loss_module = LossModule()
ratio = 0.5

ARGS = {
    'model': model,
    'loss_module': loss_module,
    'ratio': ratio
}
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 Architect — 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 Architect 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
LossPredLoss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
haizailache999/AutoAL/nets_lossprediction.py
code served (permissive licence) · get_code("e1fafd5b592a9eb4")
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 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)

# The function expects:
# - input: a tensor with even batch size, used for arithmetic operations
# - target: a tensor with same shape as input, used for arithmetic operations
# - margin: a float (default 1.0)
# - reduction: a string, either 'mean' or 'none' (default 'mean')

# Create tensors with even batch size (batch=4, features=3)
batch_size = 4
feature_dim = 3

input_tensor = torch.randn(batch_size, feature_dim)
target_tensor = torch.randn(batch_size, feature_dim)

ARGS = {
    'input': input_tensor,
    'target': target_tensor,
    'margin': 1.0,
    'reduction': 'mean'
}
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 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
get_lossnet Ran
ran; our contract draft was wrong, not the code
haizailache999/AutoAL/nets_lossprediction.py
code served (permissive licence) · get_code("6ecad90c508f92d4")
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 LossNet. 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)

# The function get_lossnet takes one parameter: 'name'
# Looking at the function body, it checks the name string against various dataset names
# and returns a LossNet instance accordingly

ARGS = {
    'name': 'CIFAR10'
}
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 LossNet — a LossNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LossNet 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
get_MNIST Not yet run
unverified (harvested, no recorded run)
haizailache999/AutoAL/data.py
code served (permissive licence) · get_code("26f20bc7d60e3102")
How it ran

no invocation recorded.

get_net_vae Not yet run
unverified (harvested, no recorded run)
haizailache999/AutoAL/nets.py
code served (permissive licence) · get_code("2c6dc918ccc7169f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
LossPredLoss 2 other papers
2 dated earlier
2107.14153 (2021-07)
Semi-Supervised Active Learning with Temporal Output Discrepancy
2203.13450 (2022-03)
A Comparative Survey of Deep Active Learning
get_MNIST 1 other paper
1 dated earlier
2203.13450 (2022-03)
A Comparative Survey of Deep Active Learning
get_net_vae 1 other paper
1 dated earlier
2203.13450 (2022-03)
A Comparative Survey of Deep Active Learning

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

As deep learning continues to evolve, the need for data efficiency becomes increasingly important. Considering labeling large datasets is both time-consuming and expensive, active learning (AL) provides a promising solution to this challenge by iteratively selecting the most informative subsets of examples to train deep neural networks, thereby reducing the labeling cost. However, the effectiveness of different AL algorithms can vary significantly across data scenarios, and determining which AL algorithm best fits a given task remains a challenging problem. This work presents the first differentiable AL strategy search method, named AutoAL, which is designed on top of existing AL sampling strategies. AutoAL consists of two neural nets, named SearchNet and FitNet, which are optimized concurrently under a differentiable bi-level optimization framework. For any given task, SearchNet and Fit-Net are iteratively co-optimized using the labeled data, learning how well a set of candidate AL algorithms perform on that task. With the optimal AL strategies identified, SearchNet selects a small subset from the unlabeled pool for querying their annotations, enabling efficient training of the task model. Experimental results demonstrate that AutoAL consistently achieves superior accuracy compared to all candidate AL algorithms and other selective AL approaches, showcasing its potential for adapting and integrating multiple existing AL methods across diverse tasks and domains. Code is available at: https://github.com/haizailache999/AutoAL.

For agents

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

get_harvested_code_for_paper("2410.13853")
get_code_for_paper("2410.13853")
have("2410.13853")

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

curl https://syntology.ai/api/ran/2410.13853.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.13853.svg)](https://syntology.ai/paper/2410.13853)

Connect an agent — have() is free.