Papers › FastSHAP: Real-Time Shapley Value Estimation

FastSHAP: Real-Time Shapley Value Estimation

15 Jul 2021ICLR 2022 4arXiv:2107.07436archive 2025-07-28

Neil Jethani, Mukund Sudarshan, Ian Covert, Su-In Lee, Rajesh Ranganath

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward pass using a learned explainer model. FastSHAP amortizes the cost of explaining many inputs via a learning approach inspired by the Shapley value's weighted least squares characterization, and it can be trained using standard stochastic gradient optimization. We compare FastSHAP to existing estimation approaches, revealing that it generates high-quality explanations with orders of magnitude speedup.

PaperPDFConference PDFCodeCode 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.

Syntology holds a reference implementation of FastSHAP, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='FastSHAP') (how to connect); the free check have('2107.07436') needs no token.

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

Code

Syntology 17 code samples harvested from 5 repositories linked to this paper: 8 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 3 repositories, 6 ran (1 with no instrument failure; 5 where Syntology's instrument failed); community (archive-listed): 8 samples from 2 repositories, 2 ran (2 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 8 samples that ran have no recorded date.

iancovert/fastshap officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 3 ran (3 instrument-failed) · 1 unverified report
iclr1814/fastshap officialmentioned in papertfSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
neiljethani/fastshap officialmentioned in papertfMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
davidenapolitano/bones mentioned on GitHubpytorchSyntology: 6 samples, 2 ran (0 instrument-failed) · 4 unverified report
tml-tuebingen/nshap mentioned on GitHubSyntology: 2 samples, 0 ran · 2 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

17 samples harvested: 8 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 9 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.

5ran · our draft was wrong
3ran
9unverified

Licence: 9 of the 17 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 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

iancovert/fastshap official repository 4 samples, 3 ran (3 instrument-failed) · 1 unverified
additive_efficient_normalization fastshap/fastshap.py ran · our draft was wrong fingerprinted MIT (permissive) · 5b767f2708a31ef1 · report fixture: signature pred:Tensor/2/float, grand:Tensor/1/float, null:Tensor/1/float · returned Tensor · level recorded, date not recorded
evaluate_explainer fastshap/fastshap.py ran · our draft was wrong MIT (permissive) · 6005c5a15fab0e21 · report fixture: signature explainer:callable/0/?, normalization:callable/0/?, x:Tensor/2/float, grand:Tensor/0/float, null:Tensor/0/float, num_players:int/0/int, inference:bool/0/bool · returned tuple · level recorded, date not recorded
multiplicative_efficient_normalization fastshap/fastshap.py ran · our draft was wrong fingerprinted MIT (permissive) · fe249de8c0fc0cfc · report fixture: signature pred:Tensor/2/float, grand:Tensor/1/float, null:Tensor/1/float · returned Tensor · level recorded, date not recorded
FastSHAP fastshap/fastshap.py unverified MIT (permissive) · 8b43828947a6b7c7 · report
iclr1814/fastshap official repository 3 samples, 2 ran (2 instrument-failed) · 1 unverified
additive_efficient_normalization fastshap_torch/fastshap.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 06435d9aa451885d · report fixture: signature pred:Tensor/2/float, grand:Tensor/1/float, null:Tensor/1/float · returned Tensor · level recorded, date not recorded
calculate_grand_coalition fastshap_torch/fastshap.py ran · our draft was wrong no licence file found · pointer only · 358ac40db44f149b · report fixture: signature x:Tensor/2/float, imputer:callable/0/?, batch_size:int/0/int, link:callable/0/?, device:device/0/? · returned Tensor · level recorded, date not recorded
validate in 313 papers fastshap_torch/fastshap.py unverified no licence file found · pointer only · b2c2b9597b4b23d6 · report
neiljethani/fastshap official repository 2 samples, 1 ran (0 instrument-failed) · 1 unverified
convert_to_linkTF fastshap/utils.py ran MIT (permissive) · 037b77174710c143 · report fixture: signature val:str/0/str · returned IdentityLinkTF · level recorded 2026-09-25
convert_to_link fastshap/utils.py unverified MIT (permissive) · 33d1e5512f0ec7db · report
davidenapolitano/bones community (archive-listed) 6 samples, 2 ran (0 instrument-failed) · 4 unverified
DatasetRepeat bones/sv/image/explainers/fastshap/fastshap.py ran no licence file found · pointer only · 03059e06ad890351 · report fixture: returned DatasetRepeat · level recorded 2026-09-22
ShapleySampler bones/sv/image/explainers/fastshap/fastshap.py ran no licence file found · pointer only · 199c28206c728459 · report fixture: returned ShapleySampler · level recorded 2026-09-22
FastSHAP bones/sv/image/explainers/fastshap/fastshap.py unverified no licence file found · pointer only · 42ef60c2b0ecb9e0 · report
calculate_grand_coalition bones/sv/image/explainers/fastshap/fastshap.py unverified no licence file found · pointer only · 77cf20ef4a967db3 · report
generate_validation_data bones/sv/image/explainers/fastshap/fastshap.py unverified no licence file found · pointer only · cb7acdc5c56bb613 · report
validate in 313 papers bones/sv/image/explainers/fastshap/fastshap.py unverified no licence file found · pointer only · 437f02dec06a9d31 · report
tml-tuebingen/nshap community (archive-listed) 2 samples, 0 ran · 2 unverified
shapley_values src/nshap/functions.py unverified MIT (permissive) · 5fbfb8cc1069b5d8 · report
validate_inputs in 5 papers src/nshap/functions.py unverified MIT (permissive) · 1e573273e29afab1 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

4 assemblies on this paper: 3 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for FastSHAP (graph method: FastSHAP), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 4 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. fastshap_loss entry · level 3 · ran · honoured contract · cf76ed8934aa1ffdd90e92c8da29c3444a5fc9dee851ecc7e33524165a71af74

3 sibling assemblies for FastSHAP (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for FastSHAP (graph method: FastSHAP). 9 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. FastSHAP entry · level 0 · unverified · 42ef60c2b0ecb9e0
  2. DatasetRepeat helper · level 1 · ran · 03059e06ad890351
  3. ShapleySampler helper · level 1 · ran · 199c28206c728459
  4. additive_efficient_normalization helper · level 1 · ran · our draft was wrong · 5b767f2708a31ef1
  5. calculate_grand_coalition helper · level 0 · unverified · 77cf20ef4a967db3
  6. evaluate_explainer helper · level 1 · ran · our draft was wrong · 6005c5a15fab0e21
  7. generate_validation_data data_transform · level 0 · unverified · cb7acdc5c56bb613
  8. multiplicative_efficient_normalization helper · level 1 · ran · our draft was wrong · fe249de8c0fc0cfc
  9. validate metric · level 0 · unverified · 437f02dec06a9d31

harvested Assembly for FastSHAP (graph method: FastSHAP). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. shapley_values entry · level 0 · unverified · 5fbfb8cc1069b5d8
  2. validate_inputs helper · level 0 · unverified · 1e573273e29afab1

harvested Assembly for FastSHAP (graph method: FastSHAP). 9 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. FastSHAP entry · level 0 · unverified · 8b43828947a6b7c7
  2. DatasetRepeat helper · level 1 · ran · 03059e06ad890351
  3. ShapleySampler helper · level 1 · ran · 199c28206c728459
  4. additive_efficient_normalization helper · level 1 · ran · our draft was wrong · 5b767f2708a31ef1
  5. calculate_grand_coalition helper · level 0 · unverified · 77cf20ef4a967db3
  6. evaluate_explainer helper · level 1 · ran · our draft was wrong · 6005c5a15fab0e21
  7. generate_validation_data helper · level 0 · unverified · cb7acdc5c56bb613
  8. multiplicative_efficient_normalization helper · level 1 · ran · our draft was wrong · fe249de8c0fc0cfc
  9. validate helper · level 0 · unverified · 437f02dec06a9d31

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="2107.07436") returns these assemblies with each brick's role and wiring (how to connect).

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