Papers › Minimizing False-Positive Attributions in Explanations of Non-Linear Models

Minimizing False-Positive Attributions in Explanations of Non-Linear Models

16 May 2025arXiv:2505.11210archive 2025-07-28

Anders Gjølbye, Stefan Haufe, Lars Kai Hansen

Suppressor variables can influence model predictions without being dependent on the target outcome and they pose a significant challenge for Explainable AI (XAI) methods. These variables may cause false-positive feature attributions, undermining the utility of explanations. Although effective remedies exist for linear models, their extension to non-linear models and to instance-based explanations has remained limited. We introduce PatternLocal, a novel XAI technique that addresses this gap. PatternLocal begins with a locally linear surrogate, e.g. LIME, KernelSHAP, or gradient-based methods, and transforms the resulting discriminative model weights into a generative representation, thereby suppressing the influence of suppressor variables while preserving local fidelity. In extensive hyperparameter optimization on the XAI-TRIS benchmark, PatternLocal consistently outperformed other XAI methods and reduced false-positive attributions when explaining non-linear tasks, thereby enabling more reliable and actionable insights.

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 11 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 11 samples from 1 repository, 8 ran (8 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

gjoelbye/patternlocal officialmentioned in papermentioned on GitHubMITSyntology: 11 samples, 8 ran (0 instrument-failed) · 3 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

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

8ran
3unverified

Licence: 0 of the 11 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 gjoelbye/patternlocal. “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.

gjoelbye/patternlocal official repository 11 samples, 8 ran (0 instrument-failed) · 3 unverified
create_combined_metric patternlocal/optimization/metrics.py ran MIT (permissive) · 00c48a4ef206beba · report fixture: signature metrics:list/1/callable, weights:list/1/float · returned function · level recorded 2026-09-25
create_experiment_config patternlocal/optimization/utils.py ran MIT (permissive) · 5904c97717c6e391 · report fixture: signature simplification:str/0/str, solver:str/0/str, backend:str/0/str, max_evals:int/0/int, metric_name:str/0/str, n_jobs:int/0/int, random_state:int/0/int · returned dict · level recorded 2026-09-25
create_ground_truth_metric patternlocal/optimization/metrics.py ran MIT (permissive) · f353af080c6b50ab · report fixture: signature explanation_weights:ndarray/1/float, instance:ndarray/1/float, ground_truth_mask:ndarray/1/bool, predict_fn:callable/0/?, X_train:ndarray/2/float, n_samples:int/0/int · returned function · level recorded 2026-09-25
evaluate_explanations_parallel patternlocal/optimization/metrics.py ran MIT (permissive) · 50eca4eb153b9c13 · report fixture: signature explainer_instance:SimpleExplainer/0/?, instances:ndarray/2/float, masks:ndarray/2/float, X_train:ndarray/2/float, y_train:ndarray/1/int, predict_fn:callable/0/?, metric_fn:callable/0/?, n_jobs:int/0/int, batch_size:int/0/int, subset_size:NoneType/0/? · returned tuple · level recorded 2026-09-25
load_optimization_results patternlocal/optimization/utils.py ran MIT (permissive) · b6e28f195b115055 · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-25
parse_parameter_dict patternlocal/optimization/utils.py ran MIT (permissive) · 16b28e46e47404e9 · report fixture: signature params:dict/0/? · returned dict · level recorded 2026-09-25
validate_array_input patternlocal/config/validation.py ran MIT (permissive) · 9e94143f78757d71 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-25
validate_fitted patternlocal/config/validation.py ran MIT (permissive) · 280645296cbb074c · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-25
create_backend patternlocal/optimization/backends.py unverified MIT (permissive) · f4541182964dfb8c · report
create_custom_search_space patternlocal/optimization/search_spaces.py unverified MIT (permissive) · ee60d051f983149f · report
get_default_search_space patternlocal/optimization/search_spaces.py unverified MIT (permissive) · fb5feb0ee52fa210 · report

Tasks

Hyperparameter Optimization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LIME

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