SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.07197 · ICML · 2020

Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search

Yong Guo, Junzhou Huang, Mingkui Tan, Yaofo Chen, Yin Zheng, Peilin Zhao, Jian Chen

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2007.07197.json · badge: /api/ran/2007.07197.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
guoyongcs/CNAS marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
ArchMaster Ran
ran on a synthesized input · constructed an object; no result was computed
guoyongcs/CNAS/cnas/model/master.py
code served (permissive licence) · get_code("ad501f0bb201bff2")
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, ArchMaster: 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)

ARGS = {
    'n_nodes': 4,
    'cur_nodes': 4,
    'n_ops': 8,
    'cur_ops': 8,
    'device': 'cpu',
    'hidden_size': 64,
    'temperature': 5.0,
    'tanh_constant': 2.25,
    'op_tanh_reduce': 1.0,
    'force_uniform': False,
}
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 ArchMaster — 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 ArchMaster 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
Genotype Ran
ran on a synthesized input · constructed an object; no result was computed
guoyongcs/CNAS/cnas/model/master.py
code served (permissive licence) · get_code("6dee04c86cdc8bfc")
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, Genotype: 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 numpy as np
from typing import List, Tuple

# Define ARGS dict with all parameters for Genotype.__init__

# Sample architecture data
named_normal_arch = [
    ('sep_conv_3x3', 0, 2),
    ('skip_connect', 1, 2),
    ('sep_conv_5x5', 0, 3),
    ('max_pool_3x3', 1, 3)
]

ordinal_normal_arch = [
    (0, 0, 2),  # sep_conv_3x3, from node 0, to node 2
    (5, 1, 2),  # skip_connect, from node 1, to node 2
    (1, 0, 3),  # sep_conv_5x5, from node 0, to node 3
    (2, 1, 3)   # max_pool_3x3, from node 1, to node 3
]

normal_concat = [2, 3]

named_reduced_arch = [
    ('max_pool_3x3', 0, 2),
    ('avg_pool_3x3', 1, 2),
    ('dil_conv_3x3', 0, 3),
    ('dil_conv_5x5', 1, 3)
]

ordinal_reduced_arch = [
    (2, 0, 2),  # max_pool_3x3, from node 0, to node 2
    (3, 1, 2),  # avg_pool_3x3, from node 1, to node 2
    (6, 0, 3),  # dil_conv_3x3, from node 0, to node 3
    (7, 1, 3)   # dil_conv_5x5, from node 1, to node 3
]

reduced_concat = [2, 3]

primitives = ['sep_conv_3x3', 'sep_conv_5x5', 'max_pool_3x3', 'avg_pool_3x3', 'none', 'skip_connect', 'dil_conv_3x3', 'dil_conv_5x5']

loose_end = False

ARGS = {
    'named_normal_arch': named_normal_arch,
    'ordinal_normal_arch': ordinal_normal_arch,
    'normal_concat': normal_concat,
    'named_reduced_arch': named_reduced_arch,
    'ordinal_reduced_arch': ordinal_reduced_arch,
    'reduced_concat': reduced_concat,
    'primitives': primitives,
    'loose_end': loose_end
}
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 Genotype — 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 Genotype 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

Neural architecture search (NAS) has become an important approach to automatically find effective architectures. To cover all possible good architectures, we need to search in an extremely large search space with billions of candidate architectures. More critically, given a large search space, we may face a very challenging issue of space explosion. However, due to the limitation of computational resources, we can only sample a very small proportion of the architectures, which provides insufficient information for the training. As a result, existing methods may often produce suboptimal architectures. To alleviate this issue, we propose a curriculum search method that starts from a small search space and gradually incorporates the learned knowledge to guide the search in a large space. With the proposed search strategy, our Curriculum Neural Architecture Search (CNAS) method significantly improves the search efficiency and finds better architectures than existing NAS methods. Extensive experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of the proposed method. * Equal contribution . This work is done when Yong Guo works as an intern in Tencent AI Lab.

For agents

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

get_harvested_code_for_paper("2007.07197")
get_code_for_paper("2007.07197")
have("2007.07197")

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

curl https://syntology.ai/api/ran/2007.07197.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.07197.svg)](https://syntology.ai/paper/2007.07197)

Connect an agent — have() is free.