Fairness in deep learning: A computational perspective

Mengnan Du, Fan Yang, Na Zou, Xia Hu

Research output: Contribution to journalReview articlepeer-review

87 Scopus citations


Fairness in deep learning has attracted tremendous attention recently, as deep learning is increasingly being used in high-stake decision making applications that affect individual lives. We provide a review covering recent progresses to tackle algorithmic fairness problems of deep learning from the computational perspective. Specifically, we show that interpretability can serve as a useful ingredient to diagnose the reasons that lead to algorithmic discrimination. We also discuss fairness mitigation approaches categorized according to three stages of deep learning life-cycle, aiming to push forward the area of fairness in deep learning and build genuinely fair and reliable deep learning systems.

Original languageEnglish (US)
Pages (from-to)25-34
Number of pages10
JournalIEEE Intelligent Systems
Issue number4
StatePublished - Jul 1 2021
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Artificial Intelligence


  • Bias
  • Deep learning
  • Dnn
  • Fairness
  • Interpretability


Dive into the research topics of 'Fairness in deep learning: A computational perspective'. Together they form a unique fingerprint.

Cite this