Papers › Interpretable Machine Learning for TabPFN

Interpretable Machine Learning for TabPFN

16 Mar 2024arXiv:2403.10923archive 2025-07-28

David Rundel, Julius Kobialka, Constantin von Crailsheim, Matthias Feurer, Thomas Nagler, David Rügamer

The recently developed Prior-Data Fitted Networks (PFNs) have shown very promising results for applications in low-data regimes. The TabPFN model, a special case of PFNs for tabular data, is able to achieve state-of-the-art performance on a variety of classification tasks while producing posterior predictive distributions in mere seconds by in-context learning without the need for learning parameters or hyperparameter tuning. This makes TabPFN a very attractive option for a wide range of domain applications. However, a major drawback of the method is its lack of interpretability. Therefore, we propose several adaptations of popular interpretability methods that we specifically design for TabPFN. By taking advantage of the unique properties of the model, our adaptations allow for more efficient computations than existing implementations. In particular, we show how in-context learning facilitates the estimation of Shapley values by avoiding approximate retraining and enables the use of Leave-One-Covariate-Out (LOCO) even when working with large-scale Transformers. In addition, we demonstrate how data valuation methods can be used to address scalability challenges of TabPFN. Our proposed methods are implemented in a package tabpfn_iml and made available at https://github.com/david-rundel/tabpfn_iml.

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

By repository: official repository: 12 samples from 1 repository, 12 ran (5 with no instrument failure; 7 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 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

david-rundel/tabpfn_iml officialmentioned in paperpytorchMITSyntology: 12 samples, 12 ran (7 instrument-failed) · 0 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

12 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran · our draft was wrong
5ran

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from david-rundel/tabpfn_iml. “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.

david-rundel/tabpfn_iml official repository 12 samples, 12 ran (7 instrument-failed) · 0 unverified
JointBCELossWithLogits tabpfniml/tabpfn_interpret/losses.py ran MIT (permissive) · 890fb6ef88c9dbef · report fixture: signature output:Tensor/3/float, target:Tensor/4/float · returned Tensor · level recorded 2026-09-24
draw_random_style tabpfniml/tabpfn_interpret/priors/differentiable_prior.py ran MIT (permissive) · 6751753e52ba3b27 · report fixture: signature dl:list/1/tuple, device:device/0/? · returned Tensor · level recorded 2026-09-24
get_NormalInitializer in 5 papers tabpfniml/tabpfn_interpret/initializers.py ran · our draft was wrong MIT (permissive) · 4c84ce37831d7194 · report fixture: signature std:float/0/float · returned function · level recorded 2026-09-26
get_append_embedding_encoder tabpfniml/tabpfn_interpret/encoders.py ran · our draft was wrong MIT (permissive) · 939b599ed6041748 · report fixture: signature encoder_creator:callable/0/? · returned function · level recorded 2026-09-24
get_cosine_schedule_with_warmup in 42 papers tabpfniml/tabpfn_interpret/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · a9c14b9fb71dbe7c · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, num_cycles:float/0/float, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-25
get_linear_schedule_with_warmup in 39 papers tabpfniml/tabpfn_interpret/utils.py ran · our draft was wrong MIT (permissive) · afba2c06a42074fe · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-26
get_model in 368 papers tabpfniml/tabpfn_interpret/priors/fast_gp.py ran MIT (permissive) · f72c39b3934d20d3 · report fixture: signature x:Tensor/2/float, y:Tensor/1/float, hyperparameters:dict/0/? · returned tuple · level recorded 2026-09-24
get_model_on_device tabpfniml/tabpfn_interpret/priors/fast_gp.py ran MIT (permissive) · cd13023248585727 · report fixture: signature x:Tensor/2/float, y:Tensor/1/float, hyperparameters:dict/0/?, device:str/0/str · returned tuple · level recorded 2026-09-24
get_normalized_encoder in 5 papers tabpfniml/tabpfn_interpret/encoders.py ran · our draft was wrong MIT (permissive) · 39f5dc76953cf6db · report fixture: signature encoder_creator:callable/0/?, data_std:float/0/float · returned function · level recorded 2026-09-24
get_normalized_uniform_encoder in 6 papers tabpfniml/tabpfn_interpret/encoders.py ran · our draft was wrong MIT (permissive) · 16eab2bd7416886c · report fixture: signature encoder_creator:callable/0/? · returned function · level recorded 2026-09-26
get_restarting_cosine_schedule_with_warmup tabpfniml/tabpfn_interpret/utils.py ran MIT (permissive) · aa7ad3fc695f98b5 · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, steps_per_restart:int/0/int, num_cycles:float/0/float, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
unpack_dict_of_tuples tabpfniml/tabpfn_interpret/priors/differentiable_prior.py ran · our draft was wrong MIT (permissive) · a20e00970d0cbf4c · report fixture: signature d:dict/0/? · returned list · level recorded 2026-09-24

Tasks

Data ValuationIn-Context LearningInterpretable Machine Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

TABPFN

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