Papers › Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations

Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations

18 Mar 2021ICCV 2021 10arXiv:2103.10226archive 2025-07-28

Pau Rodriguez, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam Laradji, Laurent Charlin, David Vazquez

Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems. In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction, providing details about the model's decision-making. Current methods tend to generate trivial counterfactuals about a model's decisions, as they often suggest to exaggerate or remove the presence of the attribute being classified. For the machine learning practitioner, these types of counterfactuals offer little value, since they provide no new information about undesired model or data biases. In this work, we identify the problem of trivial counterfactual generation and we propose DiVE to alleviate it. DiVE learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss to uncover multiple valuable explanations about the model's prediction. Further, we introduce a mechanism to prevent the model from producing trivial explanations. Experiments on CelebA and Synbols demonstrate that our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods. Code is available at https://github.com/ElementAI/beyond-trivial-explanations.

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.

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

Code

The archive's official repository (ElementAI/beyond-trivial-explanations) was not harvested; the 10 samples below come from 2 community repositories.

Syntology 10 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 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: community (archive-listed): 10 samples from 2 repositories, 6 ran (1 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.

ElementAI/beyond-trivial-explanations officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
issamlaradji/ssr mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
servicenow/beyond-trivial-explanations mentioned on GitHubpytorchSyntology: not harvested report
sobieskibj/rcsb mentioned on GitHubpytorchSyntology: 9 samples, 5 ran (5 instrument-failed) · 4 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

10 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 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 · our draft was wrong
4ran; the contract check could not run
1ran
4unverified

Licence: 9 of the 10 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; 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.

issamlaradji/ssr community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
cons_features_loss src/losses.py ran Apache-2.0 (permissive) · 88def237af56a05a · report fixture: returned Tensor · level recorded 2026-09-22
sobieskibj/rcsb community (archive-listed) 9 samples, 5 ran (5 instrument-failed) · 4 unverified
_cumulative_sum_threshold src/explainers/base.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · c4ba5f856f01c3c0 · report fixture: signature values:Tensor/2/float, percentile:int/0/int · returned Tensor · level recorded 2026-09-22
_get_last_conv_layer src/explainers/base.py ran · our draft was wrong no licence file found · pointer only · 5c104de03088fbae · report fixture: signature module:callable/0/? · returned Conv2d · level recorded 2026-09-22
_normalize_scale src/explainers/base.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · f3a716fb8b80641a · report fixture: signature attr:Tensor/3/float, scale_factor:Tensor/1/float · returned Tensor · level recorded 2026-09-22
expand_from_cell_view src/explainers/base.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · cf4c30b4c9dde913 · report fixture: signature cell_view:Tensor/3/float, cell_size:int/0/int · returned Tensor · level recorded 2026-09-22
sum_into_cell_view src/explainers/base.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · f123902550a574d0 · report fixture: signature attribution_map:Tensor/3/float, cell_size:int/0/int, half_cell_view:bool/0/bool · returned Tensor · level recorded 2026-09-22
AttributionMethod src/explainers/base.py unverified no licence file found · pointer only · 89a32ba43743ecf6 · report
ClassifierBase src/explainers/base.py unverified no licence file found · pointer only · 73d849a584e707b8 · report
_get_layers_v2 src/explainers/base.py unverified no licence file found · pointer only · b2063be99abaab6c · report
normalize_attr src/explainers/base.py unverified no licence file found · pointer only · f7b412e61259110d · 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. 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.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

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

one of 2 siblings

  1. cons_features_loss entry · level 1 · ran · 88def237af56a05a

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

one of 2 siblings

  1. AttributionMethod entry · level 0 · unverified · 89a32ba43743ecf6
  2. ClassifierBase helper · level 0 · unverified · 73d849a584e707b8
  3. _get_last_conv_layer helper · level 1 · ran · our draft was wrong · 5c104de03088fbae
  4. _get_layers_v2 helper · level 0 · unverified · b2063be99abaab6c
  5. expand_from_cell_view helper · level 1 · ran; the contract check could not run (RAISES) · cf4c30b4c9dde913
  6. normalize_attr helper · level 0 · unverified · f7b412e61259110d
  7. sum_into_cell_view helper · level 1 · ran; the contract check could not run (RAISES) · f123902550a574d0
  8. _cumulative_sum_threshold helper · level 1 · ran; the contract check could not run (RAISES) · c4ba5f856f01c3c0
  9. _normalize_scale helper · level 1 · ran; the contract check could not run (RAISES) · f3a716fb8b80641a

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="2103.10226") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AttributeBIG-bench Machine LearningDecision MakingDiversity

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.

Methods

Counterfactuals

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