Explanation and Fairness in Unsupervised Learning


Overview: Unsupervised learning approaches such as clustering are extensively used in AI with explanation and fairness emerging as important challenges. We cover explainable and fair unsupervised learning from multiple perspectives such as the philosophical under-pinnings, algorithmic details and application areas.


Bio: Ian Davidson: I am a Professor in the department of computer science at the University of California, Davis since 2009 (and before that an assistant and associated Professor). I teach AI, ML and for the past decade a course on ethics and AI/Technology. My research is a mix of fundamental algorithmic contributions to unsupervised learning (clustering and outlier detection) and supervised learning (transfer, active learning) and more practical applications (with others) in neuroscience and intelligent tutoring. With regard to fairness and explanation in unsupervised learning, I have published papers at NIPS 2018, IJCAI 2018, AAAI 2020 and ECAI 2020 on the topic and I have grants from NSF on core research on the topic and NIH to apply XAI to precision medicine.

My website is here my google scholar page is here.


Slides To Be Posted


Tutorial Outline and References


The tutorial will consist of three parts: i) Legal, Philosophical and Ethical Overviews and Motivations, ii) Algorithmic Details and iii) Applications and Future Work.


Motivations (15 minutes)

            –  Legal (in California, USA and Europe), ethical and philosophical definitions of fairness 
and explanations. 

            –  Why is fairness and explanation so necessary for unsupervised learning.

            –  The notion of protected state variables (PSV). Examples of individual level and group level unfairness 

Connection to Utilitarianism and Deontological schools of normative ethics.
The need for explanations to algorithm designer, domain scientists and public.

Algorithmic Details (60 minutes)

            –  The two approaches for adding fairness and explanation to algorithms - (apriori) fairness/explanation by-design and (aposteri) post-processing to increase fairness/explanation. 

            –  Fairness in Clustering

                         Fairness - Seminal paper encoding disparate impact in clustering [6] for classic centroid based methods. 

                         Extensions for efficiency [1] to allow multi-state [19], multiple [2] PSVs. 

                         Fairness methods for graph based [16] and other clustering algorithms [5]. 

                         Emerging work on individual level fairness [21] [17]. 

                         Algorithm independent methods of fairness - post-processing to ensure fairness 

            – Explanation in Clustering

  Explanation - Classic Work (Conceptual Clustering) [13] [18].

    Explanation using feature spaces [4].

    Explanation using alternative feature sets [10], [20], [8]. 

            –  Fairness and Explanation in Emerging Unsupervised Learning Settings.

Outlier detection [7] [11].
 Nearest neighbor search [15].   Embedding [3]. 

            –  The Connections Between Fairness and Explanation.

                Future Directions and Applications (15 minutes)

                  Applications and Transitions into Industry

                          IBM’s AI Fairness 360 toolkit

                         Accenture’s Fairness verification toolkit 

                 Open Research Questions