MétaCan
Menu
Back to cohort

Addressing Stability in Classifier Explanations

2021· article· en· W4205723429 on OpenAlex
Siavash Samiei, Nasrin Baratalipour, Pranjul Yadav, Amitabha Roy, Dake He

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venue2021 IEEE International Conference on Big Data (Big Data) · 2021
Typearticle
Languageen
FieldComputer Science
TopicExplainable Artificial Intelligence (XAI)
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsShapley valueComputer scienceClassifier (UML)Artificial neural networkArtificial intelligenceMachine learningStability (learning theory)Monte Carlo methodAlgorithmMathematicsMathematical economicsGame theoryStatistics

Abstract

fetched live from OpenAlex

Machine learning based classifiers are often a black box when considering the contribution of inputs to the output probability of a label, especially with complex non-linear models such as neural networks. A popular way to explain machine learning model outputs in a model agnostic manner is through the use of Shapley values. For our use case of abuse fighting in digital advertisements, one primary impediment of using Shapley values in explanations was a problem of instability. Specifically, the instability problem manifests as explanations for the same example varying greatly due to random sampling in the algorithm. We found it useful to view this problem explicitly as Monte Carlo integration in the form of averaging the model output while varying only a subset of features in the example to be explained. In turn, this guides the number of samples needed to achieve a stable estimate of individual Shapley values and unlocked the use of Shapley value based explainers for our models as well as classifiers in general, including neural networks.

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.

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)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication, Open science
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 score0.959
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.003
Open science0.0080.003
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.001

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 head0.728
GPT teacher head0.429
Teacher spread0.298 · 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