Papers › FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation

FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation

30 Jun 2025arXiv:2506.24125archive 2025-07-28

Jiacheng Cui, Xinyue Bi, Yaxin Luo, Xiaohan Zhao, Jiacheng Liu, Zhiqiang Shen

Residual connection has been extensively studied and widely applied at the model architecture level. However, its potential in the more challenging data-centric approaches remains unexplored. In this work, we introduce the concept of Data Residual Matching for the first time, leveraging data-level skip connections to facilitate data generation and mitigate data information vanishing. This approach maintains a balance between newly acquired knowledge through pixel space optimization and existing core local information identification within raw data modalities, specifically for the dataset distillation task. Furthermore, by incorporating optimization-level refinements, our method significantly improves computational efficiency, achieving superior performance while reducing training time and peak GPU memory usage by 50%. Consequently, the proposed method Fast and Accurate Data Residual Matching for Dataset Distillation (FADRM) establishes a new state-of-the-art, demonstrating substantial improvements over existing methods across multiple dataset benchmarks in both efficiency and effectiveness. For instance, with ResNet-18 as the student model and a 0.8% compression ratio on ImageNet-1K, the method achieves 47.7% test accuracy in single-model dataset distillation and 50.0% in multi-model dataset distillation, surpassing RDED by +5.7% and outperforming state-of-the-art multi-model approaches, EDC and CV-DD, by +1.4% and +4.0%. Code is available at: https://github.com/Jiacheng8/FADRM.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 12 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 11 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 17 ran (5 with no instrument failure; 12 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 17 samples that ran has no recorded date.

jiacheng8/fadrm officialmentioned in paperpytorchMITSyntology: 18 samples, 17 ran (12 instrument-failed) · 1 unverified 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

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 12 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
11ran · our draft was wrong
1ran; the contract check could not run
1ran
1unverified

Licence: 3 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from jiacheng8/fadrm. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

jiacheng8/fadrm official repository 18 samples, 17 ran (12 instrument-failed) · 1 unverified
DenseNet121 in 32 papers models/densenet.py ran · our draft was wrong MIT (permissive) · 3da7ee44118b27ad · report fixture: signature ncls:int/0/int · returned DenseNet · level recorded 2026-09-24
DenseNet169 in 23 papers models/densenet.py ran · our draft was wrong MIT (permissive) · 339dfa096b3c4a02 · report fixture: signature ncls:int/0/int · returned DenseNet · level recorded 2026-09-24
DenseNet201 in 22 papers models/densenet.py ran · our draft was wrong MIT (permissive) · e28ebe17022741b6 · report fixture: signature ncls:int/0/int · returned DenseNet · level recorded 2026-09-24
ResNet18 in 174 papers models/resnet.py ran · our draft was wrong MIT (permissive) · c2749ad43673e986 · report fixture: signature ncls:int/0/int · returned ResNet · level recorded 2026-09-24
ResNet34 in 91 papers models/resnet.py ran · our draft was wrong MIT (permissive) · f9e75567dfd01367 · report fixture: signature ncls:int/0/int · returned ResNet · level recorded 2026-09-24
ResNet50 in 83 papers models/resnet.py ran · our draft was wrong MIT (permissive) · 71310b3a95d5c6eb · report fixture: signature ncls:int/0/int · returned ResNet · level recorded 2026-09-24
count_multiplications recover/recover.py ran · honoured contract fingerprinted MIT (permissive) · ca73dd5ac9ee210f · report fixture: signature start:int/0/int, target:int/0/int · returned int · level recorded 2026-09-24
cutmix in 11 papers relabel/utils_fkd.py ran · our draft was wrong MIT (permissive) · b07a34e357aed3db · report fixture: signature images:Tensor/4/float, args:Args/0/?, rand_index:NoneType/0/?, lam:NoneType/0/?, bbox:NoneType/0/? · returned tuple · level recorded 2026-09-24
format_int_to_str recover/utils_recover.py ran · our draft was wrong fingerprinted MIT (permissive) · b97000ad1f1f7bba · report fixture: signature number:int/0/int · returned str · level recorded 2026-09-24
get_FKD_info relabel/utils_fkd.py ran · honoured contract MIT (permissive) · 370445b84099fd37 · report fixture: signature fkd_path:str/0/str · returned tuple · level recorded 2026-09-24
get_lambda in 8 papers models/util.py ran · honoured contract fingerprinted MIT (permissive) · ba1399ac9cd62aa7 · report fixture: signature alpha:float/0/float · returned float · level recorded 2026-09-24
get_second_idx recover/utils_recover.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 25dda4be04d5c390 · report fixture: signature all_idx:list/1/int, exclude_idx:int/0/int · returned int · level recorded 2026-09-24
is_special_epoch validate/train_fkd.py ran · violated contract fingerprinted MIT (permissive) · cd4d8e43e2ff286b · report fixture: signature epoch:int/0/int, total_epochs:int/0/int · returned bool · level recorded 2026-09-22
lr_policy in 6 papers recover/utils_recover.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 38fd828e9ae4636a · report fixture: signature lr_fn:callable/0/? · returned function · level recorded 2026-09-22
mixup_process in 6 papers models/util.py ran MIT (permissive) · bf057d506488cd4c · report fixture: signature out:Tensor/2/float, target_reweighted:Tensor/2/float, teacher_out_reweighted:Tensor/2/float, lam:float/0/float · returned tuple · level recorded 2026-09-24
rand_bbox in 63 papers relabel/utils_fkd.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 0756a99508caf42c · report fixture: signature size:tuple/1/int, lam:float/0/float · returned tuple · level recorded, date not recorded
to_one_hot in 44 papers
census: 5 implementations from 6 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
models/util.py ran · our draft was wrong MIT (permissive) · 4f312e21745a6f61 · report fixture: signature inp:Tensor/1/int, num_classes:int/0/int · returned Tensor · level recorded 2026-09-24
validate in 313 papers recover/recover.py unverified MIT (permissive) here; the stored copy is pointer only · 230fb2e9963063c9 · report

Tasks

Computational EfficiencyDataset Distillation

1 archive task tag without a task page not shown.

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