SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.04151 · 2020

Embedding Propagation: Smoother Manifold for Few-Shot Classification

arXiv · PDF · Open in the Atlas

Code that ran

1 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/2003.04151.json · badge: /api/ran/2003.04151.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
ElementAI/embedding-propagation canonical (classifier label)
classifier basis: census
1 ran · 5 no recorded run
FunctionStatusWhere it lives
embedding_propagation Ran
ran on a synthesized input
ElementAI/embedding-propagation/embedding_propagation/embedding_propagation.py
code served (permissive licence) · get_code("f48530a1f6a2b0f6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a small embedding tensor of shape (n, c) where n=2 samples, c=4 dimensions
x = torch.randn(2, 4)

# Set alpha as a smoothing factor (scalar)
alpha = 0.99

# Set rbf_scale parameter for the RBF kernel
rbf_scale = 1.0

# Set norm_prop flag for normalization
norm_prop = False

# Pre-compute propagator (optional, can be None to compute on the fly)
propagator = None

ARGS = {
    "x": x,
    "alpha": alpha,
    "rbf_scale": rbf_scale,
    "norm_prop": norm_prop,
    "propagator": propagator,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
batch_embedding_propagation Not yet run
unverified (harvested, no recorded run)
ElementAI/embedding-propagation/embedding_propagation/batch_embedding_propagation.py
code served (permissive licence) · get_code("50ed5f95e6f08a9f")
How it ran

no invocation recorded.

batch_get_similarity_matrix Not yet run
unverified (harvested, no recorded run)
ElementAI/embedding-propagation/embedding_propagation/batch_embedding_propagation.py
code served (permissive licence) · get_code("083f1d0c7625f238")
How it ran

no invocation recorded.

batch_global_consistency Not yet run
unverified (harvested, no recorded run)
ElementAI/embedding-propagation/embedding_propagation/batch_embedding_propagation.py
code served (permissive licence) · get_code("78f86f12b89abb6a")
How it ran

no invocation recorded.

get_similarity_matrix Not yet run
unverified (harvested, no recorded run)
ElementAI/embedding-propagation/embedding_propagation/embedding_propagation.py
code served (permissive licence) · get_code("f0b6f084f1c88a64")
How it ran

no invocation recorded.

label_propagation Not yet run
unverified (harvested, no recorded run)
ElementAI/embedding-propagation/embedding_propagation/embedding_propagation.py
code served (permissive licence) · get_code("30976420278e4a1c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Few-shot classification is challenging because the data distribution of the training set can be widely different to the test set as their classes are disjoint. This distribution shift often results in poor generalization. Manifold smoothing has been shown to address the distribution shift problem by extending the decision boundaries and reducing the noise of the class representations. Moreover, manifold smoothness is a key factor for semi-supervised learning and transductive learning algorithms. In this work, we propose to use embedding propagation as an unsupervised non-parametric regularizer for manifold smoothing in few-shot classification. Embedding propagation leverages interpolations between the extracted features of a neural network based on a similarity graph. We empirically show that embedding propagation yields a smoother embedding manifold. We also show that applying embedding propagation to a transductive classifier achieves new state-of-the-art results in mini-Imagenet, tiered-Imagenet, Imagenet-FS, and CUB. Furthermore, we show that embedding propagation consistently improves the accuracy of the models in multiple semi-supervised learning scenarios by up to 16\% points. The proposed embedding propagation operation can be easily integrated as a non-parametric layer into a neural network. We provide the training code and usage examples at https://github.com/ElementAI/embedding-propagation.

For agents

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

get_harvested_code_for_paper("2003.04151")
get_code_for_paper("2003.04151")
have("2003.04151")

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

curl https://syntology.ai/api/ran/2003.04151.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.04151.svg)](https://syntology.ai/paper/2003.04151)

Connect an agent — have() is free.