MétaCan
Menu
Back to cohort
Record W4391986976 · doi:10.48550/arxiv.2402.11729

Prospector Heads: Generalized Feature Attribution for Large Models & Data

2024· preprint· en· W4391986976 on OpenAlexaff
Gautam Machiraju, Alexander Derry, Arjun Desai, Neel Guha, Amir-Hossein Karimi, James Zou, Russ B Altman, Christopher Ré, Parag Mallick

Bibliographic record

VenuePubMed · 2024
Typepreprint
Languageen
FieldComputer Science
TopicImage Retrieval and Classification Techniques
Canadian institutionsUniversity of Waterloo
FundersOffice of Naval ResearchU.S. Army Combat Capabilities Development CommandNational Science FoundationNational Institutes of HealthVMwareAccenture
KeywordsAttributionFeature (linguistics)Computer sciencePattern recognition (psychology)Artificial intelligencePsychologySocial psychologyPhilosophyLinguistics

Abstract

fetched live from OpenAlex

Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical domains. Current methods for feature attribution, which rely on "explaining" the predictions of end-to-end classifiers, suffer from imprecise feature localization and are inadequate for use with small sample sizes and high-dimensional datasets due to computational challenges. We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods that can be applied to any encoder and any data modality. Prospector heads generalize across modalities through experiments on sequences (text), images (pathology), and graphs (protein structures), outperforming baseline attribution methods by up to 26.3 points in mean localization AUPRC. We also demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data. Through their high performance, flexibility, and generalizability, prospectors provide a framework for improving trust and transparency for ML models in complex domains.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.047
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
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 score0.010
Threshold uncertainty score0.055

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.047
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.003
Bibliometrics0.0020.002
Science and technology studies0.0010.002
Scholarly communication0.0030.007
Open science0.0040.007
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0100.004

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 head0.146
GPT teacher head0.322
Teacher spread0.175 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
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
Published2024
Admission routes1
Has abstractyes

Explore more

Same venuePubMedSame topicImage Retrieval and Classification TechniquesFrench-language works237,207