Papers › Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with...

Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration

7 Jun 2023arXiv:2306.04621archive 2025-07-28

Emanuel Sanchez Aimar, Nathaniel Helgesen, Yonghao Xu, Marco Kuhlmann, Michael Felsberg

Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers. This problem is often aggravated by discrepancies between labeled and unlabeled class distributions, leading to biased pseudo-labels, neglect of rare classes, and poorly calibrated probabilities. To address these issues, we introduce Flexible Distribution Alignment (FlexDA), a novel adaptive logit-adjusted loss framework designed to dynamically estimate and align predictions with the actual distribution of unlabeled data and achieve a balanced classifier by the end of training. FlexDA is further enhanced by a distillation-based consistency loss, promoting fair data usage across classes and effectively leveraging underconfident samples. This method, encapsulated in ADELLO (Align and Distill Everything All at Once), proves robust against label shift, significantly improves model calibration in LTSSL contexts, and surpasses previous state-of-of-art approaches across multiple benchmarks, including CIFAR100-LT, STL10-LT, and ImageNet127, addressing class imbalance challenges in semi-supervised learning. Our code is available at https://github.com/emasa/ADELLO-LTSSL.

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="2306.04621")

Code

Syntology Ran 10 of 16 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 7 ran; community (archive-listed): 4 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

emasa/adello-ltssl officialmentioned in papermentioned on GitHubpytorchMIT report
emasa/balpoe-calibratedlt mentioned on GitHubpytorchMIT 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

16 samples harvested; 10 ran; 1 honoured the contract we drafted; 6 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
4ran · our draft was wrong
5ran
6unverified

Licence: 0 of the 16 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

array_to_bytes emasa/adello-ltssl/preprocess/preprocess_superb.py official repository ran MIT (permissive) · dc61eede543c56fc · report
bytes_to_array emasa/adello-ltssl/preprocess/preprocess_superb.py official repository ran MIT (permissive) · b19e0120c50d4fd0 · report
comatch_contrastive_loss emasa/adello-ltssl/semilearn/algorithms/comatch/comatch.py official repository ran · honoured contract MIT (permissive) · 3346c66c873fff6a · report
read_TextClassificationDatasets emasa/adello-ltssl/preprocess/preprocess_aclimdb.py official repository ran · our draft was wrong MIT (permissive) · d954c448e1eee8c4 · report
read_aclImdb emasa/adello-ltssl/preprocess/preprocess_aclimdb.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · eed03e5ff5639e09 · report
resize_pos_embed_vit emasa/adello-ltssl/semilearn/nets/utils.py official repository ran MIT (permissive) · 4c0668013863ad3f · report
select_data emasa/adello-ltssl/preprocess/preprocess_aclimdb.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 05dda2f18675eb59 · report
compute_adello_adjustment_dist emasa/adello-ltssl/semilearn/imb_algorithms/adello/utils.py official repository unverified MIT (permissive) · fa53db62463b7abb · report
compute_alpha_factor emasa/adello-ltssl/semilearn/imb_algorithms/adello/utils.py official repository unverified MIT (permissive) · a8c4746a14905352 · report
compute_divergences emasa/adello-ltssl/semilearn/imb_algorithms/adello/utils.py official repository unverified MIT (permissive) · dbd9d3802a1d7ba1 · report
load_checkpoint emasa/adello-ltssl/semilearn/nets/utils.py official repository unverified MIT (permissive) · b158ea331635a6c9 · report
load_checkpoint_totally emasa/adello-ltssl/semilearn/nets/utils.py official repository unverified MIT (permissive) · ce75a85f590aa980 · report
accuracy emasa/balpoe-calibratedlt/model/metric.py community (archive-listed) ran MIT (permissive) · 1c1fdcd838303a0d · report
focal_loss emasa/balpoe-calibratedlt/model/loss.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 4dcf06ba28983266 · report
top_k_acc emasa/balpoe-calibratedlt/model/metric.py community (archive-listed) ran MIT (permissive) · c642158604bebe8a · report
init_weights emasa/balpoe-calibratedlt/model/model.py community (archive-listed) unverified MIT (permissive) · 0933d643f92c12aa · report

Tasks

Data Augmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

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