MétaCan
Menu
Back to cohort

Conventional Zero-Shot Learning with Semantic Graph-Enriched Non-Adversarial Synthetic Features

2025· article· W7131240494 on OpenAlexaff
Md Shakil Ahamed Shohag, Q. M. Jonathan Wu, Farhad Pourpanah

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsQueen's UniversityUniversity of Windsor
Fundersnot available
KeywordsGenerative grammarAdversarial systemClassifier (UML)Semantic featureFeature (linguistics)Training setGraph

Abstract

fetched live from OpenAlex

Adversarial training-based generative methods have shown strong performance in Zero-Shot Learning (ZSL), but they often come with significant drawbacks — including training instability and high computational cost. These approaches typically use the same feature generation pipeline for both Conventional ZSL (CZSL), where test classes are strictly unseen, and Generalized ZSL (GZSL), where both seen and unseen classes are present during inference. In this work, we argue that such frameworks are unnecessarily expensive for CZSL setups, where the primary objective is accurate recognition of unseen classes. We propose CZSL-SGNSF, a non-adversarial generative method that synthesizes unseen visual features and further enhances them through semantic graph propagation by enabling knowledge transfers across related unseen categories. For classification, we introduce a classifier trained jointly with cross-entropy and KL-divergence objectives on visual-semantic contrast. Extensive experiments on SUN, AwA2, and CUB demonstrate that our approach surpasses state-of-the-art adversarial methods in CZSL performance with significantly lower computational overhead for feature synthesis, while achieving promising results in both CZSL and GZSL compared to non-adversarial methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.911
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.012
GPT teacher head0.249
Teacher spread0.237 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicDomain Adaptation and Few-Shot LearningFrench-language works237,207