Papers › Layer-wise Linear Mode Connectivity

Layer-wise Linear Mode Connectivity

13 Jul 2023arXiv:2307.06966archive 2025-07-28

Linara Adilova, Maksym Andriushchenko, Michael Kamp, Asja Fischer, Martin Jaggi

Averaging neural network parameters is an intuitive method for fusing the knowledge of two independent models. It is most prominently used in federated learning. If models are averaged at the end of training, this can only lead to a good performing model if the loss surface of interest is very particular, i.e., the loss in the midpoint between the two models needs to be sufficiently low. This is impossible to guarantee for the non-convex losses of state-of-the-art networks. For averaging models trained on vastly different datasets, it was proposed to average only the parameters of particular layers or combinations of layers, resulting in better performing models. To get a better understanding of the effect of layer-wise averaging, we analyse the performance of the models that result from averaging single layers, or groups of layers. Based on our empirical and theoretical investigation, we introduce a novel notion of the layer-wise linear connectivity, and show that deep networks do not have layer-wise barriers between them.

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: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 18 samples from 1 repository, 13 ran (13 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

link-er/layer-wise-lmc officialmentioned in paperpytorchSyntology: 18 samples, 13 ran (0 instrument-failed) · 5 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: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

13ran
5unverified

Licence: 18 of the 18 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 link-er/layer-wise-lmc. “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.

link-er/layer-wise-lmc official repository 18 samples, 13 ran (0 instrument-failed) · 5 unverified
extract_column LLMC/layer_cumulative_heatmap.py ran no licence file found · pointer only · 44f01653b8cf1975 · report fixture: signature dict:dict/0/?, c_id:int/0/int · returned ndarray · level recorded 2026-09-24
flatten_weights LLMC/nets_function_similarity.py ran no licence file found · pointer only · 40cc1995de8f761a · report fixture: signature state_dict:dict/0/? · returned ndarray · level recorded 2026-09-24
function_similarity LLMC/nets_function_similarity.py ran no licence file found · pointer only · b592d76b4f6b4201 · report fixture: signature model:callable/0/?, state1:dict/0/?, state2:dict/0/?, dataloader:list/1/tuple · returned tuple · level recorded 2026-09-24
get_barrier LLMC/barrier.py ran no licence file found · pointer only · 9eb1fab42625b164 · report fixture: signature model:callable/0/?, sd1:dict/0/?, sd2:dict/0/?, trainloader:list/1/tuple, testloader:list/1/tuple, criterion:callable/0/?, amount:int/0/int, no_endpoints:bool/0/bool · returned dict · level recorded 2026-09-24
get_fed_cifar10_loaders LLMC/datasets.py ran no licence file found · pointer only · 3f4f5555d18d1bba · report fixture: signature client_id:int/0/int, data_root:str/0/str, batch_size:int/0/int, imagenet_resize:bool/0/bool · returned tuple · level recorded 2026-09-24
get_full_fed_cifar10_loaders LLMC/datasets.py ran no licence file found · pointer only · 49957b7ee1419059 · report fixture: signature clients_num:int/0/int, data_root:str/0/str, batch_size:int/0/int, imagenet_resize:bool/0/bool · returned tuple · level recorded 2026-09-24
get_layer_barrier LLMC/barrier.py ran no licence file found · pointer only · 192d974fb6f9cd09 · report fixture: signature model:callable/0/?, layers:list/1/str, sd1:dict/0/?, sd2:dict/0/?, trainloader:list/1/tuple, testloader:list/1/tuple, criterion:callable/0/?, amount:int/0/int, no_endpoints:bool/0/bool · returned dict · level recorded 2026-09-24
get_layer_blocks LLMC/pythia_models.py ran no licence file found · pointer only · a970412946104eb4 · report fixture: signature state_dict:dict/0/? · returned OrderedDict · level recorded 2026-09-24
get_layer_random_barrier LLMC/barrier.py ran no licence file found · pointer only · bf025bbca4033969 · report fixture: signature model:callable/0/?, layers:list/1/str, state:dict/0/?, rnd_point:dict/0/?, trainloader:list/1/tuple, testloader:list/1/tuple, criterion:callable/0/?, amount:int/0/int, no_endpoints:bool/0/bool · returned dict · level recorded 2026-09-24
get_states LLMC/layer_cumulative_compute.py ran no licence file found · pointer only · 728827a3563e0670 · report fixture: returned tuple · level recorded 2026-09-24
get_states LLMC/layerwise_nonconvex_compute.py ran no licence file found · pointer only · b5348d1b58a5796c · report fixture: returned tuple · level recorded 2026-09-24
interpolate_state_dicts LLMC/pythia_models.py ran no licence file found · pointer only · e66ee958fa003cab · report fixture: signature state_dict_1:dict/0/?, state_dict_2:dict/0/?, lambd:float/0/float · returned dict · level recorded 2026-09-24
model_predictions LLMC/nets_function_similarity.py ran no licence file found · pointer only · ead38901ea916085 · report fixture: signature net:callable/0/?, dataloader:list/1/tuple · returned tuple · level recorded 2026-09-24
create_data_for_heatmap LLMC/layer_cumulative_heatmap.py unverified no licence file found · pointer only · 7e43290c7da2aebf · report
create_data_for_heatmap LLMC/layerwise_nonconvex_heatmap.py unverified no licence file found · pointer only · bb2dace4d2cf2be6 · report
create_data_for_heatmap LLMC/layerwise_robustness_plot.py unverified no licence file found · pointer only · 34569af015a2523b · report
get_cifar10_loaders LLMC/datasets.py unverified no licence file found · pointer only · 2d5f7b5584850a83 · report
get_wikitext_data LLMC/pythia_models.py unverified no licence file found · pointer only · eb9415ddd7c070b8 · report

Tasks

Federated LearningLinear Mode Connectivity

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