Papers › On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with...

On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features

23 Nov 2021arXiv:2111.12128archive 2025-07-28

Emanuele Rossi, Henry Kenlay, Maria I. Gorinova, Benjamin Paul Chamberlain, Xiaowen Dong, Michael Bronstein

While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph. In many real-world applications, however, features are only partially available; for example, in social networks, age and gender are available only for a small subset of users. We present a general approach for handling missing features in graph machine learning applications that is based on minimization of the Dirichlet energy and leads to a diffusion-type differential equation on the graph. The discretization of this equation produces a simple, fast and scalable algorithm which we call Feature Propagation. We experimentally show that the proposed approach outperforms previous methods on seven common node-classification benchmarks and can withstand surprisingly high rates of missing features: on average we observe only around 4% relative accuracy drop when 99% of the features are missing. Moreover, it takes only 10 seconds to run on a graph with ∼2.5M nodes and ∼123M edges on a single GPU.

PaperPDFConference PDFCodeCode 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 14 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 12 ran (11 with no instrument failure; 1 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.

twitter-research/feature-propagation officialmentioned on GitHubpytorchApache-2.0Syntology: 14 samples, 12 ran (1 instrument-failed) · 2 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

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 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.

1ran · our draft was wrong
11ran
2unverified

Licence: 4 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, 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 twitter-research/feature-propagation. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

twitter-research/feature-propagation official repository 14 samples, 12 ran (1 instrument-failed) · 2 unverified
ex_relu src/baselines/gcn_mf.py ran fingerprinted Apache-2.0 (permissive) · cc49cd8a589e02de · report fixture: signature mu:Tensor/2/float, sigma:Tensor/2/float · returned Tensor · level recorded 2026-09-25
get_conv in 21 papers src/models.py ran Apache-2.0 (permissive) · 338d87d585e0b11d · report fixture: signature conv_type:str/0/str, input_dim:int/0/int, output_dim:int/0/int · returned SAGEConv · level recorded 2026-09-24
get_mask in 119 papers
census: 9 implementations from 10 papers, 9 distinct outputs across 7 buckets, one shared input per bucket
src/utils.py ran Apache-2.0 (permissive) · 12003dcf4549f5a3 · report fixture: signature idx:Tensor/1/int, num_nodes:int/0/int · returned Tensor · level recorded 2026-09-26
get_missing_feature_mask src/utils.py ran Apache-2.0 (permissive) · bdff77b67175af09 · report fixture: signature rate:float/0/float, n_nodes:int/0/int, n_features:int/0/int, type:str/0/str · returned Tensor · level recorded 2026-09-24
inference_full_batch src/evaluation.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 09a790aab330a10e · report fixture: signature model:callable/0/?, x:Tensor/2/float, edge_index:Tensor/2/int · returned Tensor · level recorded 2026-09-26
inference_sampled src/evaluation.py ran Apache-2.0 (permissive) · 17f844b866904bc9 · report fixture: signature model:callable/0/?, x:Tensor/2/float, inference_loader:list/1/tuple, device:device/0/? · returned Tensor · level recorded 2026-09-26
init_gmm src/baselines/gcn_mf.py ran Apache-2.0 (permissive) · 56a5ef8b43881fac · report fixture: signature features:ndarray/2/float, n_components:int/0/int · returned GaussianMixture · level recorded 2026-09-25
keep_only_largest_connected_component src/data_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 9e01cbb3f563b6df · report fixture: signature dataset:DummyDataset/0/? · returned DummyDataset · level recorded 2026-09-26
mean_filling src/filling_strategies.py ran Apache-2.0 (permissive) · b8ff0add0a440e77 · report fixture: signature X:Tensor/2/float, feature_mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24
random_filling src/filling_strategies.py ran fingerprinted Apache-2.0 (permissive) · 6161e8125aef4044 · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-24
test in 377 papers src/evaluation.py ran Apache-2.0 (permissive) · 917430c937090e71 · report fixture: signature model:callable/0/?, x:Tensor/2/float, data:callable/0/?, logits:NoneType/0/?, evaluator:Evaluator/0/?, inference_loader:list/1/tuple, device:str/0/str · returned tuple · level recorded 2026-09-24
zero_filling src/filling_strategies.py ran fingerprinted Apache-2.0 (permissive) · 603473b3dc2838d0 · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_component in 8 papers src/data_utils.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · c68140584cc0e991 · report
get_largest_connected_component in 7 papers src/data_utils.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · b36878b25e3455a3 · report

Tasks

Node Classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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