Papers › UNREAL:Unlabeled Nodes Retrieval and Labeling for Heavily-imbalanced Node Classification

UNREAL:Unlabeled Nodes Retrieval and Labeling for Heavily-imbalanced Node Classification

18 Mar 2023arXiv:2303.10371archive 2025-07-28

Liang Yan, Shengzhong Zhang, Bisheng Li, Min Zhou, Zengfeng Huang

Extremely skewed label distributions are common in real-world node classification tasks. If not dealt with appropriately, it significantly hurts the performance of GNNs in minority classes. Due to its practical importance, there have been a series of recent research devoted to this challenge. Existing over-sampling techniques smooth the label distribution by generating ``fake'' minority nodes and synthesizing their features and local topology, which largely ignore the rich information of unlabeled nodes on graphs. In this paper, we propose UNREAL, an iterative over-sampling method. The first key difference is that we only add unlabeled nodes instead of synthetic nodes, which eliminates the challenge of feature and neighborhood generation. To select which unlabeled nodes to add, we propose geometric ranking to rank unlabeled nodes. Geometric ranking exploits unsupervised learning in the node embedding space to effectively calibrates pseudo-label assignment. Finally, we identify the issue of geometric imbalance in the embedding space and provide a simple metric to filter out geometrically imbalanced nodes. Extensive experiments on real-world benchmark datasets are conducted, and the empirical results show that our method significantly outperforms current state-of-the-art methods consistent on different datasets with different imbalance ratios.

PaperPDFCodeCode Syntology ranMethod as code

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 15 code samples harvested from 1 repository linked to this paper: 10 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 10 ran (4 with no instrument failure; 6 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yanliang3612/UNREAL officialmentioned on GitHubpytorchSyntology: 15 samples, 10 ran (6 instrument-failed) · 5 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

15 samples harvested: 10 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
3ran; the contract check could not run
4ran
5unverified

Licence: 0 of the 15 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 yanliang3612/UNREAL. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

yanliang3612/UNREAL official repository 15 samples, 10 ran (6 instrument-failed) · 5 unverified
Classifier in 72 papers models/Summer.py ran · metamorphic tier: deterministic MIT (permissive) · 21b8e2937b061ca5 · report fixture: returned Classifier · level recorded 2026-09-22
GNN in 23 papers models/Summer.py ran · metamorphic tier: deterministic MIT (permissive) · a0f51d43b2936c11 · report fixture: returned GNN · level recorded 2026-09-22
Imbalance models/Summer.py ran MIT (permissive) · d0e375f51c18030a · report fixture: returned Imbalance · level recorded 2026-09-22
Summer models/Summer.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1cc5c8c084587cd8 · report fixture: returned Summer · level recorded 2026-09-22
_resolve_device models/Summer.py ran · our draft was wrong MIT (permissive) · 0314bb33efbb8ff6 · report fixture: signature device_name:str/0/str · returned device · level recorded 2026-09-22
_split_metrics models/Summer.py ran; the contract check could not run (RAISES) MIT (permissive) · 00ae29dfec5bcea4 · report fixture: signature predictions:Tensor/1/int, labels:Tensor/1/int, mask:Tensor/1/bool · returned tuple · level recorded 2026-09-22
compute_accuracy in 81 papers models/Summer.py ran; the contract check could not run (RAISES) MIT (permissive) · 00a374c740d0efb3 · report fixture: signature predictions:Tensor/1/int, labels:Tensor/1/int, train_mask:Tensor/1/bool, val_mask:Tensor/1/bool, test_mask:Tensor/1/bool · returned tuple · level recorded 2026-09-22
config_to_string models/Summer.py ran · our draft was wrong MIT (permissive) · 862acaca85666e46 · report fixture: signature args:Namespace/0/? · returned str · level recorded 2026-09-22
random_seed models/Summer.py ran; the contract check could not run (DEP_MISSING) · metamorphic tier: well formed MIT (permissive) · 2ebbc35773aa6632 · report fixture: signature repetition:int/0/int, dataset:str/0/str · returned int · level recorded 2026-09-22
rbo_score models/Summer.py ran · our draft was wrong fingerprinted MIT (permissive) · 3c7f729e8b77f2e8 · report fixture: signature first_ranking:ndarray/1/int, second_ranking:ndarray/1/int, persistence:float/0/float · returned float · level recorded 2026-09-22
Embedder in 18 papers models/Summer.py unverified MIT (permissive) · 68c3a90607b726f4 · report
Planetoid models/Summer.py unverified MIT (permissive) · fbb5df7d27b6feca · report
SummerTrainer models/Summer.py unverified MIT (permissive) · 1a38e65656984fc5 · report
reset in 5 papers models/Summer.py unverified MIT (permissive) · 8988d78678494da0 · report
set_random_seeds models/Summer.py unverified MIT (permissive) · 497de9f0b9677508 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for pseudo-label alignment, node reordering, and ambiguity filtering (graph method: pseudo-label alignment, node reordering, and ambiguity filtering). 15 bricks; individually on a fixture: 10 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. SummerTrainer entry · level 0 · unverified · 1a38e65656984fc5
  2. Classifier model · level 1 · ran · 21b8e2937b061ca5
  3. Embedder helper · level 0 · unverified · 68c3a90607b726f4
  4. GNN helper · level 1 · ran · a0f51d43b2936c11
  5. Planetoid helper · level 0 · unverified · fbb5df7d27b6feca
  6. Summer model · level 1 · ran · 1cc5c8c084587cd8
  7. random_seed helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 2ebbc35773aa6632
  8. rbo_score helper · level 1 · ran · our draft was wrong · 3c7f729e8b77f2e8
  9. set_random_seeds helper · level 0 · unverified · 497de9f0b9677508
  10. _resolve_device helper · level 1 · ran · our draft was wrong · 0314bb33efbb8ff6
  11. compute_accuracy helper · level 1 · ran; the contract check could not run (RAISES) · 00a374c740d0efb3
  12. config_to_string helper · level 1 · ran · our draft was wrong · 862acaca85666e46
  13. Imbalance data_transform · level 1 · ran · d0e375f51c18030a
  14. reset helper · level 0 · unverified · 8988d78678494da0
  15. _split_metrics helper · level 1 · ran; the contract check could not run (RAISES) · 00ae29dfec5bcea4

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.10371") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Node ClassificationPseudo LabelRetrieval

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