SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.11181 · NeurIPS · 2021

Realistic Evaluation of Transductive Few-Shot Learning

Malik Boudiaf, Éts Montreal, Pablo Piantanida, Ismail Ben, Ayed Montreal, Olivier Veilleux

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 4 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2204.11181.json · badge: /api/ran/2204.11181.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
oveilleux/realistic_transductive_few_shot canonical (classifier label)
classifier basis: classifier_2025
6 ran · 4 no recorded run
FunctionStatusWhere it lives
Logger Ran
ran on a synthesized input · constructed an object; no result was computed
oveilleux/realistic_transductive_few_shot/src/methods/tim.py
pointer only (licence: NONE) · get_code("c2bb0431f66349c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TIM Ran
ran on a synthesized input · constructed an object; no result was computed
oveilleux/realistic_transductive_few_shot/src/methods/tim.py
pointer only (licence: NONE) · get_code("9612cc426ca84971")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_features Ran
ran; our contract draft was wrong, not the code
oveilleux/realistic_transductive_few_shot/src/methods/tim.py
pointer only (licence: NONE) · get_code("1e25337f3b8c7d05")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_cond_entropy Ran
ran; our contract draft was wrong, not the code
oveilleux/realistic_transductive_few_shot/src/methods/tim.py
pointer only (licence: NONE) · get_code("a611fe8fce609022")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_mi Ran
ran; our contract draft was wrong, not the code
oveilleux/realistic_transductive_few_shot/src/methods/tim.py
pointer only (licence: NONE) · get_code("da0a1da72474e584")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_one_hot Ran
ran; our contract draft was wrong, not the code
oveilleux/realistic_transductive_few_shot/src/methods/tim.py
pointer only (licence: NONE) · get_code("a03c85ae21c3b667")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ALPHA_TIM Not yet run
unverified (harvested, no recorded run)
oveilleux/realistic_transductive_few_shot/src/methods/tim.py
pointer only (licence: NONE) · get_code("e01d7f2363beb45a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

convert_prob_to_samples Not yet run
unverified (harvested, no recorded run)
oveilleux/realistic_transductive_few_shot/src/datasets/sampler.py
pointer only (licence: NONE) · get_code("6a236e22aa59cecc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_dirichlet_query_dist Not yet run
unverified (harvested, no recorded run)
oveilleux/realistic_transductive_few_shot/src/datasets/sampler.py
pointer only (licence: NONE) · get_code("fdf1fa9384ed9dcb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_entropy Not yet run
unverified (harvested, no recorded run)
oveilleux/realistic_transductive_few_shot/src/methods/tim.py
pointer only (licence: NONE) · get_code("e6a5040deda27fed")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oveilleux/realistic_transductive_few_shot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_one_hot
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later · 1 only as an assembly brick
2008.11297 (2020-08)
Transductive Information Maximization For Few-Shot Learning
2206.04679 (2022-06)
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Transductive inference is widely used in few-shot learning, as it leverages the statistics of the unlabeled query set of a few-shot task, typically yielding substantially better performances than its inductive counterpart. The current few-shot benchmarks use perfectly class-balanced tasks at inference. We argue that such an artificial regularity is unrealistic, as it assumes that the marginal label probability of the testing samples is known and fixed to the uniform distribution. In fact, in realistic scenarios, the unlabeled query sets come with arbitrary and unknown label marginals. We introduce and study the effect of arbitrary class distributions within the query sets of few-shot tasks at inference, removing the class-balance artefact. Specifically, we model the marginal probabilities of the classes as Dirichlet-distributed random variables, which yields a principled and realistic sampling within the simplex. This leverages the current few-shot benchmarks, building testing tasks with arbitrary class distributions. We evaluate experimentally state-of-the-art transductive methods over 3 widely used data sets, and observe, surprisingly, substantial performance drops, even below inductive methods in some cases. Furthermore, we propose a generalization of the mutual-information loss, based on α-divergences, which can handle effectively class-distribution variations. Empirically, we show that our transductive α-divergence optimization outperforms state-of-the-art methods across several data sets, models and few-shot settings. Our code is publicly available at https://github.com/oveilleux/Realistic_Transductive_Few_Shot.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.11181")
get_code_for_paper("2204.11181")
have("2204.11181")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.11181.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.11181.svg)](https://syntology.ai/paper/2204.11181)

Connect an agent — have() is free.