Papers › Meta-Learning Probabilistic Inference For Prediction

Meta-Learning Probabilistic Inference For Prediction

24 May 2018ICLR 2019 5arXiv:1805.09921archive 2025-07-28

Jonathan Gordon, John Bronskill, Matthias Bauer, Sebastian Nowozin, Richard E. Turner

This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing probabilistic interpretations of meta-learning to cover a broad class of methods. 2) We introduce VERSA, an instance of the framework employing a flexible and versatile amortization network that takes few-shot learning datasets as inputs, with arbitrary numbers of shots, and outputs a distribution over task-specific parameters in a single forward pass. VERSA substitutes optimization at test time with forward passes through inference networks, amortizing the cost of inference and relieving the need for second derivatives during training. 3) We evaluate VERSA on benchmark datasets where the method sets new state-of-the-art results, handles arbitrary numbers of shots, and for classification, arbitrary numbers of classes at train and test time. The power of the approach is then demonstrated through a challenging few-shot ShapeNet view reconstruction task.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1805.09921")

Code

Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.

By repository: official repository: 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Gordonjo/versa officialmentioned in papermentioned on GitHubtfMIT 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

8 samples harvested; 0 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8unverified

Licence: 0 of the 8 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 Gordonjo/versa. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

augment_character_set Gordonjo/versa/src/omniglot.py official repository unverified MIT (permissive) · 199ffb3539b8e99c · report
convert_index_to_angle Gordonjo/versa/src/shapenet.py official repository unverified MIT (permissive) · 556efaa3287037b7 · report
extract_data Gordonjo/versa/src/omniglot.py official repository unverified MIT (permissive) · 2408a27b9438a36d · report
gaussian_log_density Gordonjo/versa/src/utilities.py official repository unverified MIT (permissive) · 6ab983fc9df0ded6 · report
multinoulli_log_density Gordonjo/versa/src/utilities.py official repository unverified MIT (permissive) · 264b32317fa04d3a · report
onehottify_2d_array Gordonjo/versa/src/mini_imagenet.py official repository unverified MIT (permissive) · 2aa09adb640c018a · report
sample_normal Gordonjo/versa/src/utilities.py official repository unverified MIT (permissive) · 4a6c83ecf1b78179 · report
shuffle_batch Gordonjo/versa/src/omniglot.py official repository unverified MIT (permissive) · f5090bc705663805 · report

Tasks

Few-Shot Image ClassificationFew-Shot LearningMeta-LearningPrediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 1-shot) Versa 1:1 Accuracy 47.8 #11 of 12 Archive leaderboard report
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 5-shot) Versa 1:1 Accuracy 61.9 #12 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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