Model Feature Attribution Drift Violations
Feature attribution drift jobs evaluate the baseline constraints provided by the
baseline configuration against the analysis results of current
MonitoringExecution
. If violations are detected, the job lists them to
the constraint_violations.json file in the execution
output location, and marks the execution status as Interpret results.
Here is the schema of the feature attribution drift violations file.
-
label
– The name of the label, job analysis configurationlabel_headers
or a placeholder such as"label0"
. -
metric_name
– The name of the explainability analysis method. Currently onlyshap
is supported. -
constraint_check_type
– The type of violation monitored. Currently onlyfeature_attribution_drift_check
is supported. -
description
– A descriptive message to explain the violation.
{ "version": "1.0", "violations": [{ "label": "string", "metric_name": "string", "constraint_check_type": "string", "description": "string" }] }
For each label in the explanations
section, the monitoring jobs calculate
the nDCG score“feature”
fields in the violation entry. The
following output provides an example of several logged violations.
{ "version": "1.0", "violations": [{ "label": "label0", "metric_name": "shap", "constraint_check_type": "feature_attribution_drift_check", "description": "Feature attribution drift 0.7639720923277322 exceeds threshold 0.9" }, { "label": "label1", "metric_name": "shap", "constraint_check_type": "feature_attribution_drift_check", "description": "Feature attribution drift 0.7323763972092327 exceeds threshold 0.9" }] }