Papers › Learning to Complement and to Defer to Multiple Users

Learning to Complement and to Defer to Multiple Users

9 Jul 2024arXiv:2407.07003archive 2025-07-28

Zheng Zhang, Wenjie Ai, Kevin Wells, David Rosewarne, Thanh-Toan Do, Gustavo Carneiro

With the development of Human-AI Collaboration in Classification (HAI-CC), integrating users and AI predictions becomes challenging due to the complex decision-making process. This process has three options: 1) AI autonomously classifies, 2) learning to complement, where AI collaborates with users, and 3) learning to defer, where AI defers to users. Despite their interconnected nature, these options have been studied in isolation rather than as components of a unified system. In this paper, we address this weakness with the novel HAI-CC methodology, called Learning to Complement and to Defer to Multiple Users (LECODU). LECODU not only combines learning to complement and learning to defer strategies, but it also incorporates an estimation of the optimal number of users to engage in the decision process. The training of LECODU maximises classification accuracy and minimises collaboration costs associated with user involvement. Comprehensive evaluations across real-world and synthesized datasets demonstrate LECODU's superior performance compared to state-of-the-art HAI-CC methods. Remarkably, even when relying on unreliable users with high rates of label noise, LECODU exhibits significant improvement over both human decision-makers alone and AI alone.

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="2407.07003")

Code

Syntology Ran 19 of 21 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 5 ran · our draft was wrong; 14 ran with no contract checked.

By repository: official repository: 21 samples from 1 repository, 19 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhengzhang37/lecodu 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

21 samples harvested; 19 ran; 0 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.

5ran · our draft was wrong
14ran
2unverified

Licence: 21 of the 21 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 zhengzhang37/lecodu. “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.

AutoContrast zhengzhang37/lecodu/utils/randaug.py official repository ran · our draft was wrong no licence file found · pointer only · 4a0ac9d611e018bc · report
Brightness zhengzhang37/lecodu/utils/randaug.py official repository ran no licence file found · pointer only · 61ed09bbdb8adb72 · report
Color zhengzhang37/lecodu/utils/randaug.py official repository ran no licence file found · pointer only · 5e4ee5c45933ae09 · report
ResNet18 zhengzhang37/lecodu/PreResNet.py official repository ran · our draft was wrong no licence file found · pointer only · 7b20f1288903c47c · report
ResNet34 zhengzhang37/lecodu/PreResNet.py official repository ran · our draft was wrong no licence file found · pointer only · eee26fa0aef03470 · report
bias_initial zhengzhang37/lecodu/utils/utils.py official repository ran fingerprinted no licence file found · pointer only · dc322bdafd96ffba · report
conv3x3 zhengzhang37/lecodu/PreResNet.py official repository ran · our draft was wrong no licence file found · pointer only · 583f9780bdd00a45 · report
debias_output zhengzhang37/lecodu/utils/utils.py official repository ran fingerprinted no licence file found · pointer only · 0f217ad023a21a61 · report
debias_pl zhengzhang37/lecodu/utils/utils.py official repository ran fingerprinted no licence file found · pointer only · 59ea92571d058dba · report
fftfreqnd zhengzhang37/lecodu/utils/fmix.py official repository ran no licence file found · pointer only · 79f12de984fe5e1c · report
fit zhengzhang37/lecodu/utils/tools.py official repository ran no licence file found · pointer only · cf3259099e459c51 · report
fmix_loss zhengzhang37/lecodu/utils/fmix.py official repository ran no licence file found · pointer only · 122df027ef4a7990 · report
get_instance_noisy_label zhengzhang37/lecodu/utils/tools.py official repository ran no licence file found · pointer only · 8f421a9c1829d948 · report
get_spectrum zhengzhang37/lecodu/utils/fmix.py official repository ran no licence file found · pointer only · eb5c9156d8d5d9c4 · report
norm zhengzhang37/lecodu/utils/tools.py official repository ran fingerprinted no licence file found · pointer only · 536c9719cc690836 · report
sample_gumbel zhengzhang37/lecodu/lecodu_chaoyang.py official repository ran · our draft was wrong no licence file found · pointer only · 7c913c414af7196f · report
unpickle zhengzhang37/lecodu/dataloader_cifar.py official repository ran no licence file found · pointer only · ef49e82a7403eee1 · report
value_to_one_hot zhengzhang37/lecodu/lecodu_chaoyang.py official repository ran no licence file found · pointer only · b66ffd33f592d1a5 · report
value_to_one_hot zhengzhang37/lecodu/train_cifar_multiusers.py official repository ran no licence file found · pointer only · deedc113c7bf508c · report
create_model zhengzhang37/lecodu/lecodu_chaoyang.py official repository unverified no licence file found · pointer only · 50ab7cb81d56353e · report
create_model zhengzhang37/lecodu/train_cifar_multiusers.py official repository unverified no licence file found · pointer only · 50915e2234edf43b · report

Tasks

Decision Making

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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