Papers › Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA

Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA

31 Oct 2024arXiv:2411.00259archive 2025-07-28

David Smerkous, Qinxun Bai, Fuxin Li

Particle-based Bayesian deep learning often requires a similarity metric to compare two networks. However, naive similarity metrics lack permutation invariance and are inappropriate for comparing networks. Centered Kernel Alignment (CKA) on feature kernels has been proposed to compare deep networks but has not been used as an optimization objective in Bayesian deep learning. In this paper, we explore the use of CKA in Bayesian deep learning to generate diverse ensembles and hypernetworks that output a network posterior. Noting that CKA projects kernels onto a unit hypersphere and that directly optimizing the CKA objective leads to diminishing gradients when two networks are very similar. We propose adopting the approach of hyperspherical energy (HE) on top of CKA kernels to address this drawback and improve training stability. Additionally, by leveraging CKA-based feature kernels, we derive feature repulsive terms applied to synthetically generated outlier examples. Experiments on both diverse ensembles and hypernetworks show that our approach significantly outperforms baselines in terms of uncertainty quantification in both synthetic and realistic outlier detection tasks.

PaperPDFCodeCode Syntology ranMethod as code

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 19 code samples harvested from 1 repository linked to this paper: 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 7 ran (2 with no instrument failure; 5 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Deep-Machine-Vision/he-cka-ensembles officialmentioned on GitHubpytorchSyntology: 19 samples, 7 ran (5 instrument-failed) · 12 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

19 samples harvested: 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 12 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.

1ran · honoured contract
1ran · our draft was wrong
4ran; the contract check could not run
1ran
12unverified

Licence: 0 of the 19 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 Deep-Machine-Vision/he-cka-ensembles. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

Deep-Machine-Vision/he-cka-ensembles official repository 19 samples, 7 ran (5 instrument-failed) · 12 unverified
EMA in 18 papers hyper/diversity/model_kernels.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 9036f42b36c62bb0 · report fixture: returned EMA · level recorded 2026-09-22
detach_diagonal hyper/diversity/model_kernels.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 17277f273917cf17 · report fixture: signature gram:Tensor/3/float, readd:bool/0/bool · returned Tensor · level recorded 2026-09-22
hyperenergy_gram hyper/diversity/model_kernels.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 09adcb1ba247435b · report fixture: signature X:Tensor/3/float, Y:Tensor/3/float, detach_diag:bool/0/bool, readd:bool/0/bool, arc_eps:float/0/float, eps:float/0/float, mhe_s:int/0/int · returned Tensor · level recorded 2026-09-22
hyperspherical_energy hyper/diversity/model_kernels.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 189230e658112733 · report fixture: signature features:Tensor/2/float, s:float/0/float, half_space:bool/0/bool, eps:float/0/float, arc_eps:float/0/float, offset:float/0/float, reduction:str/0/str, remove_diag:bool/0/bool, detach_right:bool/0/bool, abs_vals:bool/0/bool, use_exp:bool/0/bool · returned Tensor · level recorded 2026-09-22
register_model_kernel hyper/diversity/model_kernels.py ran · our draft was wrong MIT (permissive) · 42842f48a3537257 · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-22
unit_vector_rows hyper/diversity/model_kernels.py ran · honoured contract fingerprinted MIT (permissive) · 0f4775316d8a360b · report fixture: signature features:Tensor/2/float, eps:float/0/float, vectorize:bool/0/bool · returned Tensor · level recorded 2026-09-22
vectorize_grams hyper/diversity/model_kernels.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · ad9c14c7c7ee4c60 · report fixture: signature gram:Tensor/3/float · returned Tensor · level recorded 2026-09-22
BaseModelKernel hyper/diversity/model_kernels.py unverified MIT (permissive) · 97d771b52d7d258e · report
FeatureKernel hyper/diversity/model_kernels.py unverified MIT (permissive) · 68f7b9162c05d546 · report
HEModelKernel hyper/diversity/model_kernels.py unverified MIT (permissive) · 893c6101f062d6e1 · report
batched_gram hyper/diversity/model_kernels.py unverified MIT (permissive) · 0323344675a6cdd0 · report
build_model_kernel hyper/diversity/model_kernels.py unverified MIT (permissive) · 88020a1f65b635e9 · report
center_gram in 6 papers hyper/diversity/model_kernels.py unverified MIT (permissive) · b2174c8f0519c0cd · report
cossim_gram hyper/diversity/model_kernels.py unverified MIT (permissive) · e1d0a2d50b1be24c · report
laplacian_gram hyper/diversity/model_kernels.py unverified MIT (permissive) · 6a5ac817802e3767 · report
learned_gram hyper/diversity/model_kernels.py unverified MIT (permissive) · 53fdc3e076551676 · report
linear_gram hyper/diversity/model_kernels.py unverified MIT (permissive) · c76a29ddc6955622 · report
log_gram hyper/diversity/model_kernels.py unverified MIT (permissive) · 79d630fbd2b5a65b · report
rbf_gram hyper/diversity/model_kernels.py unverified MIT (permissive) · 7b85bee07d9485cd · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Hyperspherical Energy Minimization of CKA (graph method: Hyperspherical Energy Minimization of CKA). 19 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. HEModelKernel entry · level 0 · unverified · 893c6101f062d6e1
  2. BaseModelKernel helper · level 0 · unverified · 97d771b52d7d258e
  3. FeatureKernel model · level 0 · unverified · 68f7b9162c05d546
  4. build_model_kernel helper · level 0 · unverified · 88020a1f65b635e9
  5. center_gram helper · level 0 · unverified · b2174c8f0519c0cd
  6. hyperspherical_energy helper · level 1 · ran; the contract check could not run (RAISES) · 189230e658112733
  7. register_model_kernel helper · level 1 · ran · our draft was wrong · 42842f48a3537257
  8. unit_vector_rows helper · level 1 · ran · honoured contract · 0f4775316d8a360b
  9. batched_gram helper · level 0 · unverified · 0323344675a6cdd0
  10. EMA helper · level 1 · ran · 9036f42b36c62bb0
  11. vectorize_grams helper · level 1 · ran; the contract check could not run (RAISES) · ad9c14c7c7ee4c60
  12. learned_gram helper · level 0 · unverified · 53fdc3e076551676
  13. cossim_gram helper · level 0 · unverified · e1d0a2d50b1be24c
  14. detach_diagonal helper · level 1 · ran; the contract check could not run (RAISES) · 17277f273917cf17
  15. hyperenergy_gram model · level 1 · ran; the contract check could not run (RAISES) · 09adcb1ba247435b
  16. laplacian_gram helper · level 0 · unverified · 6a5ac817802e3767
  17. linear_gram helper · level 0 · unverified · c76a29ddc6955622
  18. log_gram helper · level 0 · unverified · 79d630fbd2b5a65b
  19. rbf_gram helper · level 0 · unverified · 7b85bee07d9485cd

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2411.00259") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Deep LearningDiversityOutlier DetectionUncertainty Quantification

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