Papers › Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

9 May 2024arXiv:2405.05695archive 2025-07-28

Yuan Gao, Weizhong Zhang, Wenhan Luo, Lin Ma, Jin-Gang Yu, Gui-Song Xia, Jiayi Ma

We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task inference cost of the primary task. While most existing auxiliary learning methods are optimization-based relying on loss weights/gradients manipulation, our method is architecture-based with a flexible asymmetric structure for the primary and auxiliary tasks, which produces different networks for training and inference. Specifically, starting from two single task networks/branches (each representing a task), we propose a novel method with evolving networks where only primary-to-auxiliary links exist as the cross-task connections after convergence. These connections can be removed during the primary task inference, resulting in a single-task inference cost. We achieve this by formulating a Neural Architecture Search (NAS) problem, where we initialize bi-directional connections in the search space and guide the NAS optimization converging to an architecture with only the single-side primary-to-auxiliary connections. Moreover, our method can be incorporated with optimization-based auxiliary learning approaches. Extensive experiments with six tasks on NYU v2, CityScapes, and Taskonomy datasets using VGG, ResNet, and ViT backbones validate the promising performance. The codes are available at https://github.com/ethanygao/Aux-NAS.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.05695")

Code

Syntology Ran 13 of 15 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 5 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ethanygao/aux-nas officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 13 ran; 1 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
7ran
2unverified

Licence: 15 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ethanygao/aux-nas. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

SingleSidedAsymmetricResidualNDDR ethanygao/aux-nas/networks/stagewise_search_aux.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · cc1d6490e45a9d27 · report
batch_norm ethanygao/aux-nas/networks/stagewise_search_aux.py official repository ran · our draft was wrong no licence file found · pointer only · 56af5b6a5714675c · report
compute_scale_and_shift ethanygao/Aux-NAS/loss/losses.py official repository ran no licence file found · pointer only · 25ba9b5031480973 · report
depth_limited_connectivity_matrix ethanygao/Aux-NAS/networks/aux_model.py official repository ran no licence file found · pointer only · 7219923056d8addc · report
entropy_loss ethanygao/aux-nas/networks/stagewise_search_aux.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · b2ce8e695ddf3a7c · report
get_logger ethanygao/Aux-NAS/utils/logger.py official repository ran no licence file found · pointer only · 8346d5d38e5f0042 · report
get_nddr ethanygao/aux-nas/networks/stagewise_search_aux.py official repository ran · our draft was wrong no licence file found · pointer only · b1af115958c103bc · report
get_optimizer_aux ethanygao/Aux-NAS/utils/optim.py official repository ran no licence file found · pointer only · 4ab0e3296c5e44f2 · report
get_optimizer_single ethanygao/Aux-NAS/utils/optim.py official repository ran no licence file found · pointer only · 7b83f79fccb2b76d · report
l1_loss ethanygao/aux-nas/networks/stagewise_search_aux.py official repository ran · our draft was wrong no licence file found · pointer only · f8b84bd1ce7b7e94 · report
layer_norm ethanygao/aux-nas/networks/stagewise_search_aux.py official repository ran · our draft was wrong no licence file found · pointer only · ddb859dc4e680704 · report
poly ethanygao/aux-nas/networks/stagewise_search_aux.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · da5bbab470adc6d7 · report
reduction_batch_based ethanygao/Aux-NAS/loss/losses.py official repository ran fingerprinted no licence file found · pointer only · e8996630fe3501e1 · report
GeneralizedMTLNASNet_L1Cut ethanygao/aux-nas/networks/stagewise_search_aux.py official repository unverified no licence file found · pointer only · dbdcd5113506addd · report
reduction_image_based ethanygao/Aux-NAS/loss/losses.py official repository unverified no licence file found · pointer only · c92f0115a72bf454 · report

Tasks

Auxiliary LearningNeural Architecture Search

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Average PoolingConvolutionDense ConnectionsDropoutFocusGlobal Average PoolingKaiming InitializationMax PoolingSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections