liveBook · Manning

Micro averaging

As explained in Build AI Drug Discovery Pipelines

Micro-averaging pools classification outcomes across classes before calculating an aggregate metric, giving more influence to frequent classes or labels.

Micro-averaging pools predictions across all classes or labels before calculating one metric. Because frequent labels contribute more observations, the result emphasizes overall instance-level performance and is useful for imbalanced multilabel activity data. section 5.4.2

Use micro-averaging when evaluation should reflect the labels occurring most often:

  • Pool true positives, false positives, and other outcome counts across classes, then calculate the metric once. section 5.4.2
  • Prefer it when common activity labels matter most or when overall multilabel performance matters more than equal performance across labels. section 5.4.2
  • Choose macro-averaging instead when rare labels deserve the same influence as frequent labels. section 5.4.2

Pooling three class results

Suppose three classes produce 90, 30, and 40 true positives, with 10, 20, and 10 false positives. Micro precision pools the counts: 160 / 200 = 0.80. Macro precision averages the class precisions, (0.90 + 0.60 + 0.80) / 3 ≈ 0.77. The higher micro value reflects the influence of the large, high-precision class. section 5.4.2

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains pooled metric calculation, class-frequency weighting, and contrast with macro-averaging through a numerical precision example.
Examples
Uses a three-class precision calculation and a multilabel CYP inhibitor evaluation workflow.
What it assumes
Assumes familiarity with classification labels and metrics such as precision or F1, while distinguishing multilabel from multiclass prediction.
What you can do after
Evaluate multilabel classifiers with metrics that reflect frequent labels and overall instance-level performance.
How it connects
Connects multilabel classification with macro-averaging, F1 score, precision, class imbalance, and activity labels.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.